Knowledge distillation (KD) is a widely adopted technique for transferring knowledge from a high-capacity teacher model to a smaller student model by aligning their output distributions. However, existing methods often underperform in fine-grained visual recognition tasks, where distinguishing subtle differences between visually similar classes is essential. This performance gap stems from the fact that conventional approaches treat the teacher's output logits as a single, undifferentiated signal-assuming all contained information is equally beneficial to the student. Consequently, student models may become overloaded with redundant signals and fail to capture the teacher's nuanced decision boundaries. To address this issue, we propose Fine-Grained Knowledge Distillation (FiGKD), a novel frequency-aware framework that decomposes a model's logits into low-frequency (content) and high-frequency (detail) components using the discrete wavelet transform (DWT). FiGKD selectively transfers only the high-frequency components, which encode the teacher's semantic decision patterns, while discarding redundant low-frequency content already conveyed through ground-truth supervision. Our approach is simple, architecture-agnostic, and requires no access to intermediate feature maps. Extensive experiments on CIFAR-100, TinyImageNet, and multiple fine-grained recognition benchmarks show that FiGKD consistently outperforms state-of-the-art logit-based and feature-based distillation methods across a variety of teacher-student configurations. These findings confirm that frequency-aware logit decomposition enables more efficient and effective knowledge transfer, particularly in resource-constrained settings.
Fine-grained Visual Recognition (FGVR) involves distinguishing between visually similar categories, which is inherently challenging due to subtle inter-class differences and the need for large, expert-annotated datasets. In domains like medical imaging, such curated datasets are unavailable due to issues like privacy concerns and high annotation costs. In such scenarios lacking labeled data, an FGVR model cannot rely on a predefined set of training labels, and hence has an unconstrained output space for predictions. We refer to this task as Vocabulary-Free FGVR (VF-FGVR), where a model must predict labels from an unconstrained output space without prior label information. While recent Multimodal Large Language Models (MLLMs) show potential for VF-FGVR, querying these models for each test input is impractical because of high costs and prohibitive inference times. To address these limitations, we introduce \textbf{Nea}rest-Neighbor Label \textbf{R}efinement (NeaR), a novel approach that fine-tunes a downstream CLIP model using labels generated by an MLLM. Our approach constructs a weakly supervised dataset from a small, unlabeled training set, leveraging MLLMs for label generation. NeaR is designed to handle the noise, stochasticity, and open-endedness inherent in labels generated by MLLMs, and establishes a new benchmark for efficient VF-FGVR.
Vision-Language Models (VLMs) have demonstrated impressive performance on various visual tasks, yet they still require adaptation on downstream tasks to achieve optimal performance. Recently, various adaptation technologies have been proposed, but we observe they often underperform in fine-grained visual recognition, which requires models to capture subtle yet discriminative features to distinguish similar sub-categories. Current adaptation methods typically rely on an alignment-based prediction framework, \ie the visual feature is compared with each class prompt for similarity calculation as the final prediction, which lacks class interaction during the forward pass. Besides, learning single uni-modal feature further restricts the model's expressive capacity. Therefore, we propose a novel mechanism, XR-VLM, to discover subtle differences by modeling cross-relationships, which specifically excels in scenarios involving multiple features. Our method introduces a unified multi-part visual feature extraction module designed to seamlessly integrate with the diverse backbones inherent in VLMs. Additionally, we develop a multi-part prompt learning module to capture multi-perspective descriptions of sub-categories. To further enhance discriminative capability, we propose a cross relationship modeling pattern that combines visual feature with all class prompt features, enabling a deeper exploration of the relationships between these two modalities. Extensive experiments have been conducted on various fine-grained datasets, and the results demonstrate that our method achieves significant improvements compared to current state-of-the-art approaches. Code will be released.
Large multimodal models (LMMs) have shown impressive capabilities in a wide range of visual tasks. However, they often struggle with fine-grained visual reasoning, failing to identify domain-specific objectives and provide justifiable explanations for their predictions. To address this, we propose a novel visual rejection sampling framework to improve the cognition and explainability of LMMs using self-synthesized data. Specifically, visual fine-tuning requires images, queries, and target answers. Our approach begins by synthesizing interpretable answers that include human-verifiable visual features. These features are based on expert-defined concepts, carefully selected based on their alignment with the image content. After each round of fine-tuning, we apply a reward model-free filtering mechanism to select the highest-quality interpretable answers for the next round of tuning. This iterative process of data synthesis and fine-tuning progressively improves the model's ability to generate accurate and reasonable explanations. Experimental results demonstrate the effectiveness of our method in improving both the accuracy and explainability of specialized visual classification tasks.
Multi-modal large language models (MLLMs) have shown remarkable abilities in various visual understanding tasks. However, MLLMs still struggle with fine-grained visual recognition (FGVR), which aims to identify subordinate-level categories from images. This can negatively impact more advanced capabilities of MLLMs, such as object-centric visual question answering and reasoning. In our study, we revisit three quintessential capabilities of MLLMs for FGVR, including object information extraction, category knowledge reserve, object-category alignment, and position of the root cause as a misalignment problem. To address this issue, we present Finedefics, an MLLM that enhances the model's FGVR capability by incorporating informative attribute descriptions of objects into the training phase. We employ contrastive learning on object-attribute pairs and attribute-category pairs simultaneously and use examples from similar but incorrect categories as hard negatives, naturally bringing representations of visual objects and category names closer. Extensive evaluations across multiple popular FGVR datasets demonstrate that Finedefics outperforms existing MLLMs of comparable parameter sizes, showcasing its remarkable efficacy. The code is available at https://github.com/PKU-ICST-MIPL/Finedefics_ICLR2025.
The exploration of automated wrist fracture recognition has gained considerable research attention in recent years. In practical medical scenarios, physicians and surgeons may lack the specialized expertise required for accurate X-ray interpretation, highlighting the need for machine vision to enhance diagnostic accuracy. However, conventional recognition techniques face challenges in discerning subtle differences in X-rays when classifying wrist pathologies, as many of these pathologies, such as fractures, can be small and hard to distinguish. This study tackles wrist pathology recognition as a fine-grained visual recognition (FGVR) problem, utilizing a limited, custom-curated dataset that mirrors real-world medical constraints, relying solely on image-level annotations. We introduce a specialized FGVR-based ensemble approach to identify discriminative regions within X-rays. We employ an Explainable AI (XAI) technique called Grad-CAM to pinpoint these regions. Our ensemble approach outperformed many conventional SOTA and FGVR techniques, underscoring the effectiveness of our strategy in enhancing accuracy in wrist pathology recognition.
Although foundational vision-language models (VLMs) have proven to be very successful for various semantic discrimination tasks, they still struggle to perform faithfully for fine-grained categorization. Moreover, foundational models trained on one domain do not generalize well on a different domain without fine-tuning. We attribute these to the limitations of the VLM's semantic representations and attempt to improve their fine-grained visual awareness using generative modeling. Specifically, we propose two novel methods: Generative Class Prompt Learning (GCPL) and Contrastive Multi-class Prompt Learning (CoMPLe). Utilizing text-to-image diffusion models, GCPL significantly improves the visio-linguistic synergy in class embeddings by conditioning on few-shot exemplars with learnable class prompts. CoMPLe builds on this foundation by introducing a contrastive learning component that encourages inter-class separation during the generative optimization process. Our empirical results demonstrate that such a generative class prompt learning approach substantially outperform existing methods, offering a better alternative to few shot image recognition challenges. The source code will be made available at: https://github.com/soumitri2001/GCPL.
Training a fine-grained image recognition model with limited data presents a significant challenge, as the subtle differences between categories may not be easily discernible amidst distracting noise patterns. One commonly employed strategy is to leverage pretrained neural networks, which can generate effective feature representations for constructing an image classification model with a restricted dataset. However, these pretrained neural networks are typically trained for different tasks than the fine-grained visual recognition (FGVR) task at hand, which can lead to the extraction of less relevant features. Moreover, in the context of building FGVR models with limited data, these irrelevant features can dominate the training process, overshadowing more useful, generalizable discriminative features. Our research has identified a surprisingly simple solution to this challenge: we introduce a regularization technique to ensure that the magnitudes of the extracted features are evenly distributed. This regularization is achieved by maximizing the uniformity of feature magnitude distribution, measured through the entropy of the normalized features. The motivation behind this regularization is to remove bias in feature magnitudes from pretrained models, where some features may be more prominent and, consequently, more likely to be used for classification. Additionally, we have developed a dynamic weighting mechanism to adjust the strength of this regularization throughout the learning process. Despite its apparent simplicity, our approach has demonstrated significant performance improvements across various fine-grained visual recognition datasets.
Text recognition in the wild is an important technique for digital maps and urban scene understanding, in which the natural resembling properties between glyphs is one of the major reasons that lead to wrong recognition results. To address this challenge, we introduce two extremely fine-grained visual recognition benchmark datasets that contain very challenging resembling glyphs (characters/letters) in the wild to be distinguished. Moreover, we propose a simple yet effective two-stage contrastive learning approach to the extremely fine-grained recognition task of resembling glyphs discrimination. In the first stage, we utilize supervised contrastive learning to leverage label information to warm-up the backbone network. In the second stage, we introduce CCFG-Net, a network architecture that integrates classification and contrastive learning in both Euclidean and Angular spaces, in which contrastive learning is applied in both supervised learning and pairwise discrimination manners to enhance the model's feature representation capability. Overall, our proposed approach effectively exploits the complementary strengths of contrastive learning and classification, leading to improved recognition performance on the resembling glyphs. Comparative evaluations with state-of-the-art fine-grained classification approaches under both Convolutional Neural Network (CNN) and Transformer backbones demonstrate the superiority of our proposed method.
Self-Supervised Learning (SSL) has become a prominent approach for acquiring visual representations across various tasks, yet its application in fine-grained visual recognition (FGVR) is challenged by the intricate task of distinguishing subtle differences between categories. To overcome this, we introduce an novel strategy that boosts SSL's ability to extract critical discriminative features vital for FGVR. This approach creates synthesized data pairs to guide the model to focus on discriminative features critical for FGVR during SSL. We start by identifying non-discriminative features using two main criteria: features with low variance that fail to effectively separate data and those deemed less important by Grad-CAM induced from the SSL loss. We then introduce perturbations to these non-discriminative features while preserving discriminative ones. A decoder is employed to reconstruct images from both perturbed and original feature vectors to create data pairs. An encoder is trained on such generated data pairs to become invariant to variations in non-discriminative dimensions while focusing on discriminative features, thereby improving the model's performance in FGVR tasks. We demonstrate the promising FGVR performance of the proposed approach through extensive evaluation on a wide variety of datasets.
The emerging task of fine-grained image classification in low-data regimes assumes the presence of low inter-class variance and large intra-class variation along with a highly limited amount of training samples per class. However, traditional ways of separately dealing with fine-grained categorisation and extremely scarce data may be inefficient under both these harsh conditions presented together. In this paper, we present a novel framework, called AD-Net, aiming to enhance deep neural network performance on this challenge by leveraging the power of Augmentation and Distillation techniques. Specifically, our approach is designed to refine learned features through self-distillation on augmented samples, mitigating harmful overfitting. We conduct comprehensive experiments on popular fine-grained image classification benchmarks where our AD-Net demonstrates consistent improvement over traditional fine-tuning and state-of-the-art low-data techniques. Remarkably, with the smallest data available, our framework shows an outstanding relative accuracy increase of up to 45 % compared to standard ResNet-50 and up to 27 % compared to the closest SOTA runner-up. We emphasise that our approach is practically architecture-independent and adds zero extra cost at inference time. Additionally, we provide an extensive study on the impact of every framework's component, highlighting the importance of each in achieving optimal performance. Source code and trained models are publicly available at github.com/demidovd98/fgic_lowd.
Understanding Activities of Daily Living (ADLs) is a crucial step for different applications including assistive robots, smart homes, and healthcare. However, to date, few benchmarks and methods have focused on complex ADLs, especially those involving multi-person interactions in home environments. In this paper, we propose a new dataset and benchmark, InteractADL, for understanding complex ADLs that involve interaction between humans (and objects). Furthermore, complex ADLs occurring in home environments comprise a challenging long-tailed distribution due to the rarity of multi-person interactions, and pose fine-grained visual recognition tasks due to the presence of semantically and visually similar classes. To address these issues, we propose a novel method for fine-grained few-shot video classification called Name Tuning that enables greater semantic separability by learning optimal class name vectors. We show that Name Tuning can be combined with existing prompt tuning strategies to learn the entire input text (rather than only learning the prompt or class names) and demonstrate improved performance for few-shot classification on InteractADL and 4 other fine-grained visual classification benchmarks. For transparency and reproducibility, we release our code at https://github.com/zanedurante/vlm_benchmark.
CLIP (Contrastive Language-Image Pre-training) uses contrastive learning from noise image-text pairs to excel at recognizing a wide array of candidates, yet its focus on broad associations hinders the precision in distinguishing subtle differences among fine-grained items. Conversely, Multimodal Large Language Models (MLLMs) excel at classifying fine-grained categories, thanks to their substantial knowledge from pre-training on web-level corpora. However, the performance of MLLMs declines with an increase in category numbers, primarily due to growing complexity and constraints of limited context window size. To synergize the strengths of both approaches and enhance the few-shot/zero-shot recognition abilities for datasets characterized by extensive and fine-grained vocabularies, this paper introduces RAR, a Retrieving And Ranking augmented method for MLLMs. We initially establish a multi-modal retriever based on CLIP to create and store explicit memory for different categories beyond the immediate context window. During inference, RAR retrieves the top-k similar results from the memory and uses MLLMs to rank and make the final predictions. Our proposed approach not only addresses the inherent limitations in fine-grained recognition but also preserves the model's comprehensive knowledge base, significantly boosting accuracy across a range of vision-language recognition tasks. Notably, our approach demonstrates a significant improvement in performance on 5 fine-grained visual recognition benchmarks, 11 few-shot image recognition datasets, and the 2 object detection datasets under the zero-shot recognition setting.
Self-supervised contrastive learning strategy has attracted remarkable attention due to its exceptional ability in representation learning. However, current contrastive learning tends to learn global coarse-grained representations of the image that benefit generic object recognition, whereas such coarse-grained features are insufficient for fine-grained visual recognition. In this paper, we present to incorporate the subtle local fine-grained feature learning into global self-supervised contrastive learning through a pure self-supervised global-local fine-grained contrastive learning framework. Specifically, a novel pretext task called Local Discrimination (LoDisc) is proposed to explicitly supervise self-supervised model's focus towards local pivotal regions which are captured by a simple-but-effective location-wise mask sampling strategy. We show that Local Discrimination pretext task can effectively enhance fine-grained clues in important local regions, and the global-local framework further refines the fine-grained feature representations of images. Extensive experimental results on different fine-grained object recognition tasks demonstrate that the proposed method can lead to a decent improvement in different evaluation settings. Meanwhile, the proposed method is also effective in general object recognition tasks.
Identifying subordinate-level categories from images is a longstanding task in computer vision and is referred to as fine-grained visual recognition (FGVR). It has tremendous significance in real-world applications since an average layperson does not excel at differentiating species of birds or mushrooms due to subtle differences among the species. A major bottleneck in developing FGVR systems is caused by the need of high-quality paired expert annotations. To circumvent the need of expert knowledge we propose Fine-grained Semantic Category Reasoning (FineR) that internally leverages the world knowledge of large language models (LLMs) as a proxy in order to reason about fine-grained category names. In detail, to bridge the modality gap between images and LLM, we extract part-level visual attributes from images as text and feed that information to a LLM. Based on the visual attributes and its internal world knowledge the LLM reasons about the subordinate-level category names. Our training-free FineR outperforms several state-of-the-art FGVR and language and vision assistant models and shows promise in working in the wild and in new domains where gathering expert annotation is arduous.
Object categories are typically organized into a multi-granularity taxonomic hierarchy. When classifying categories at different hierarchy levels, traditional uni-modal approaches focus primarily on image features, revealing limitations in complex scenarios. Recent studies integrating Vision-Language Models (VLMs) with class hierarchies have shown promise, yet they fall short of fully exploiting the hierarchical relationships. These efforts are constrained by their inability to perform effectively across varied granularity of categories. To tackle this issue, we propose a novel framework (HGCLIP) that effectively combines CLIP with a deeper exploitation of the Hierarchical class structure via Graph representation learning. We explore constructing the class hierarchy into a graph, with its nodes representing the textual or image features of each category. After passing through a graph encoder, the textual features incorporate hierarchical structure information, while the image features emphasize class-aware features derived from prototypes through the attention mechanism. Our approach demonstrates significant improvements on 11 diverse visual recognition benchmarks. Our codes are fully available at https://github.com/richard-peng-xia/HGCLIP.
Generalized category discovery (GCD) is a recently proposed open-world task. Given a set of images consisting of labeled and unlabeled instances, the goal of GCD is to automatically cluster the unlabeled samples using information transferred from the labeled dataset. The unlabeled dataset comprises both known and novel classes. The main challenge is that unlabeled novel class samples and unlabeled known class samples are mixed together in the unlabeled dataset. To address the GCD without knowing the class number of unlabeled dataset, we propose a co-training-based framework that encourages clustering consistency. Specifically, we first introduce weak and strong augmentation transformations to generate two sufficiently different views for the same sample. Then, based on the co-training assumption, we propose a consistency representation learning strategy, which encourages consistency between feature-prototype similarity and clustering assignment. Finally, we use the discriminative embeddings learned from the semi-supervised representation learning process to construct an original sparse network and use a community detection method to obtain the clustering results and the number of categories simultaneously. Extensive experiments show that our method achieves state-of-the-art performance on three generic benchmarks and three fine-grained visual recognition datasets. Especially in the ImageNet-100 data set, our method significantly exceeds the best baseline by 15.5\% and 7.0\% on the \texttt{Novel} and \texttt{All} classes, respectively.
The challenge in fine-grained visual categorization lies in how to explore the subtle differences between different subclasses and achieve accurate discrimination. Previous research has relied on large-scale annotated data and pre-trained deep models to achieve the objective. However, when only a limited amount of samples is available, similar methods may become less effective. Diffusion models have been widely adopted in data augmentation due to their outstanding diversity in data generation. However, the high level of detail required for fine-grained images makes it challenging for existing methods to be directly employed. To address this issue, we propose a novel approach termed the detail reinforcement diffusion model~(DRDM), which leverages the rich knowledge of large models for fine-grained data augmentation and comprises two key components including discriminative semantic recombination (DSR) and spatial knowledge reference~(SKR). Specifically, DSR is designed to extract implicit similarity relationships from the labels and reconstruct the semantic mapping between labels and instances, which enables better discrimination of subtle differences between different subclasses. Furthermore, we introduce the SKR module, which incorporates the distributions of different datasets as references in the feature space. This allows the SKR to aggregate the high-dimensional distribution of subclass features in few-shot FGVC tasks, thus expanding the decision boundary. Through these two critical components, we effectively utilize the knowledge from large models to address the issue of data scarcity, resulting in improved performance for fine-grained visual recognition tasks. Extensive experiments demonstrate the consistent performance gain offered by our DRDM.
Recently, vision Transformers (ViTs) have been actively applied to fine-grained visual recognition (FGVR). ViT can effectively model the interdependencies between patch-divided object regions through an inherent self-attention mechanism. In addition, patch selection is used with ViT to remove redundant patch information and highlight the most discriminative object patches. However, existing ViT-based FGVR models are limited to single-scale processing, and their fixed receptive fields hinder representational richness and exacerbate vulnerability to scale variability. Therefore, we propose multi-scale patch selection (MSPS) to improve the multi-scale capabilities of existing ViT-based models. Specifically, MSPS selects salient patches of different scales at different stages of a multi-scale vision Transformer (MS-ViT). In addition, we introduce class token transfer (CTT) and multi-scale cross-attention (MSCA) to model cross-scale interactions between selected multi-scale patches and fully reflect them in model decisions. Compared to previous single-scale patch selection (SSPS), our proposed MSPS encourages richer object representations based on feature hierarchy and consistently improves performance from small-sized to large-sized objects. As a result, we propose M2Former, which outperforms CNN-/ViT-based models on several widely used FGVR benchmarks.
Inspired by the fact that human brains can emphasize discriminative parts of the input and suppress irrelevant ones, substantial local mechanisms have been designed to boost the development of computer vision. They can not only focus on target parts to learn discriminative local representations, but also process information selectively to improve the efficiency. In terms of application scenarios and paradigms, local mechanisms have different characteristics. In this survey, we provide a systematic review of local mechanisms for various computer vision tasks and approaches, including fine-grained visual recognition, person re-identification, few-/zero-shot learning, multi-modal learning, self-supervised learning, Vision Transformers, and so on. Categorization of local mechanisms in each field is summarized. Then, advantages and disadvantages for every category are analyzed deeply, leaving room for exploration. Finally, future research directions about local mechanisms have also been discussed that may benefit future works. To the best our knowledge, this is the first survey about local mechanisms on computer vision. We hope that this survey can shed light on future research in the computer vision field.