Human-Object Interaction detection is a holistic visual recognition task that entails object detection as well as interaction classification. Previous works of HOI detection has been addressed by the various compositions of subset predictions, e.g., Image -> HO -> I, Image -> HI -> O. Recently, transformer based architecture for HOI has emerged, which directly predicts the HOI triplets in an end-to-end fashion (Image -> HOI). Motivated by various inference paths for HOI detection, we propose cross-path consistency learning (CPC), which is a novel end-to-end learning strategy to improve HOI detection for transformers by leveraging augmented decoding paths. CPC learning enforces all the possible predictions from permuted inference sequences to be consistent. This simple scheme makes the model learn consistent representations, thereby improving generalization without increasing model capacity. Our experiments demonstrate the effectiveness of our method, and we achieved significant improvement on V-COCO and HICO-DET compared to the baseline models. Our code is available at https://github.com/mlvlab/CPChoi.
Large language models (LLMs) have made significant advancements in natural language understanding. However, through that enormous semantic representation that the LLM has learnt, is it somehow possible for it to understand images as well? This work investigates this question. To enable the LLM to process images, we convert them into a representation given by Scalable Vector Graphics (SVG). To study what the LLM can do with this XML-based textual description of images, we test the LLM on three broad computer vision tasks: (i) visual reasoning and question answering, (ii) image classification under distribution shift, few-shot learning, and (iii) generating new images using visual prompting. Even though we do not naturally associate LLMs with any visual understanding capabilities, our results indicate that the LLM can often do a decent job in many of these tasks, potentially opening new avenues for research into LLMs' ability to understand image data. Our code, data, and models can be found here https://github.com/mu-cai/svg-llm.
Many recent advancements in Computer Vision are attributed to large datasets. Open-source software packages for Machine Learning and inexpensive commodity hardware have reduced the barrier of entry for exploring novel approaches at scale. It is possible to train models over millions of examples within a few days. Although large-scale datasets exist for image understanding, such as ImageNet, there are no comparable size video classification datasets. In this paper, we introduce YouTube-8M, the largest multi-label video classification dataset, composed of ~8 million videos (500K hours of video), annotated with a vocabulary of 4800 visual entities. To get the videos and their labels, we used a YouTube video annotation system, which labels videos with their main topics. While the labels are machine-generated, they have high-precision and are derived from a variety of human-based signals including metadata and query click signals. We filtered the video labels (Knowledge Graph entities) using both automated and manual curation strategies, including asking human raters if the labels are visually recognizable. Then, we decoded each video at one-frame-per-second, and used a Deep CNN pre-trained on ImageNet to extract the hidden representation immediately prior to the classification layer. Finally, we compressed the frame features and make both the features and video-level labels available for download. We trained various (modest) classification models on the dataset, evaluated them using popular evaluation metrics, and report them as baselines. Despite the size of the dataset, some of our models train to convergence in less than a day on a single machine using TensorFlow. We plan to release code for training a TensorFlow model and for computing metrics.
Images from outdoor scenes may be taken under various weather conditions. It is well studied that weather impacts the performance of computer vision algorithms and needs to be handled properly. However, existing algorithms model weather condition as a discrete status and estimate it using multi-label classification. The fact is that, physically, specifically in meteorology, weather are modeled as a continuous and transitional status. Instead of directly implementing hard classification as existing multi-weather classification methods do, we consider the physical formulation of multi-weather conditions and model the impact of physical-related parameter on learning from the image appearance. In this paper, we start with solid revisit of the physics definition of weather and how it can be described as a continuous machine learning and computer vision task. Namely, we propose to model the weather uncertainty, where the level of probability and co-existence of multiple weather conditions are both considered. A Gaussian mixture model is used to encapsulate the weather uncertainty and a uncertainty-aware multi-weather learning scheme is proposed based on prior-posterior learning. A novel multi-weather co-presence estimation transformer (MeFormer) is proposed. In addition, a new multi-weather co-presence estimation (MePe) dataset, along with 14 fine-grained weather categories and 16,078 samples, is proposed to benchmark both conventional multi-label weather classification task and multi-weather co-presence estimation task. Large scale experiments show that the proposed method achieves state-of-the-art performance and substantial generalization capabilities on both the conventional multi-label weather classification task and the proposed multi-weather co-presence estimation task. Besides, modeling weather uncertainty also benefits adverse-weather semantic segmentation.
Generative adversarial networks (GANs) are one of the most popular methods for generating images today. While impressive results have been validated by visual inspection, a number of quantitative criteria have emerged only recently. We argue here that the existing ones are insufficient and need to be in adequation with the task at hand. In this paper we introduce two measures based on image classification---GAN-train and GAN-test, which approximate the recall (diversity) and precision (quality of the image) of GANs respectively. We evaluate a number of recent GAN approaches based on these two measures and demonstrate a clear difference in performance. Furthermore, we observe that the increasing difficulty of the dataset, from CIFAR10 over CIFAR100 to ImageNet, shows an inverse correlation with the quality of the GANs, as clearly evident from our measures.
In this paper, we propose a new measure to gauge the complexity of image classification problems. Given an annotated image dataset, our method computes a complexity measure called the cumulative spectral gradient (CSG) which strongly correlates with the test accuracy of convolutional neural networks (CNN). The CSG measure is derived from the probabilistic divergence between classes in a spectral clustering framework. We show that this metric correlates with the overall separability of the dataset and thus its inherent complexity. As will be shown, our metric can be used for dataset reduction, to assess which classes are more difficult to disentangle, and approximate the accuracy one could expect to get with a CNN. Results obtained on 11 datasets and three CNN models reveal that our method is more accurate and faster than previous complexity measures.
Few-Shot Learning is the challenge of training a model with only a small amount of data. Many solutions to this problem use meta-learning algorithms, i.e. algorithms that learn to learn. By sampling few-shot tasks from a larger dataset, we can teach these algorithms to solve new, unseen tasks. This document reports my work on meta-learning algorithms for Few-Shot Computer Vision. This work was done during my internship at Sicara, a French company building image recognition solutions for businesses. It contains: 1. an extensive review of the state-of-the-art in few-shot computer vision; 2. a benchmark of meta-learning algorithms for few-shot image classification; 3. the introduction to a novel meta-learning algorithm for few-shot object detection, which is still in development.
Satellite images hold great promise for continuous environmental monitoring and earth observation. Occlusions cast by clouds, however, can severely limit coverage, making ground information extraction more difficult. Existing pipelines typically perform cloud removal with simple temporal composites and hand-crafted filters. In contrast, we cast the problem of cloud removal as a conditional image synthesis challenge, and we propose a trainable spatiotemporal generator network (STGAN) to remove clouds. We train our model on a new large-scale spatiotemporal dataset that we construct, containing 97640 image pairs covering all continents. We demonstrate experimentally that the proposed STGAN model outperforms standard models and can generate realistic cloud-free images with high PSNR and SSIM values across a variety of atmospheric conditions, leading to improved performance in downstream tasks such as land cover classification.
Convolutional networks are at the center of best-in-class computer vision applications for a wide assortment of undertakings. Since 2014, a profound amount of work began to make better convolutional architectures, yielding generous additions in different benchmarks. Albeit expanded model size and computational cost will, in general, mean prompt quality increases for most undertakings but, the architectures now need to have some additional information to increase the performance. I show evidence that with the amalgamation of content-based image similarity and deep learning models, we can provide the flow of information which can be used in making clustered learning possible. The paper shows how training of sub-dataset clusters not only reduces the cost of computation but also increases the speed of evaluating and tuning a model on the given dataset.
We study a referential game (a type of signaling game) where two agents communicate with each other via a discrete bottleneck to achieve a common goal. In our referential game, the goal of the speaker is to compose a message or a symbolic representation of "important" image patches, while the task for the listener is to match the speaker's message to a different view of the same image. We show that it is indeed possible for the two agents to develop a communication protocol without explicit or implicit supervision. We further investigate the developed protocol and show the applications in speeding up recent Vision Transformers by using only important patches, and as pre-training for downstream recognition tasks (e.g., classification). Code available at https://github.com/kampta/PatchGame.
We demonstrate the use of DeCAF and Improved Fisher Vector image features to classify clothing texture. The issue of choosing clothes is a problem for the blind every day. This work attempts to solve the issue with a finger-mounted camera and state-of-the-art classification algorithms. To evaluate our solution, we collected 520 close-up images across 29 pieces of clothing. We contribute (1) the HCTD, an image dataset taken with a NanEyeGS camera, a camera small enough to be mounted on the finger, and (2) evaluations of state-of-the-art recognition algorithms applied to our dataset - achieving an accuracy >95%. Throughout the paper, we will discuss previous work, evaluate the current work, and finally, suggest the project's future direction.
We propose a simple and effective method to estimate the uncertainty of closed-source deep neural network image classification models. Given a base image, our method creates multiple transformed versions and uses them to query the top-1 prediction of the closed-source model. We demonstrate significant improvements in the calibration of uncertainty estimates compared to the naive baseline of assigning 100\% confidence to all predictions. While we initially explore Gaussian perturbations, our empirical findings indicate that natural transformations, such as rotations and elastic deformations, yield even better-calibrated predictions. Furthermore, through empirical results and a straightforward theoretical analysis, we elucidate the reasons behind the superior performance of natural transformations over Gaussian noise. Leveraging these insights, we propose a transfer learning approach that further improves our calibration results.
We explore the universality of neural encodings in convolutional neural networks trained on image classification tasks. We develop a procedure to directly compare the learned weights rather than their representations. It is based on a factorization of spatial and channel dimensions and measures the similarity of aligned weight covariances. We show that, for a range of layers of VGG-type networks, the learned eigenvectors appear to be universal across different natural image datasets. Our results suggest the existence of a universal neural encoding for natural images. They explain, at a more fundamental level, the success of transfer learning. Our work shows that, instead of aiming at maximizing the performance of neural networks, one can alternatively attempt to maximize the universality of the learned encoding, in order to build a principled foundation model.
Weakly-supervised semantic segmentation (WSSS) has recently gained much attention for its promise to train segmentation models only with image-level labels. Existing WSSS methods commonly argue that the sparse coverage of CAM incurs the performance bottleneck of WSSS. This paper provides analytical and empirical evidence that the actual bottleneck may not be sparse coverage but a global thresholding scheme applied after CAM. Then, we show that this issue can be mitigated by satisfying two conditions; 1) reducing the imbalance in the foreground activation and 2) increasing the gap between the foreground and the background activation. Based on these findings, we propose a novel activation manipulation network with a per-pixel classification loss and a label conditioning module. Per-pixel classification naturally induces two-level activation in activation maps, which can penalize the most discriminative parts, promote the less discriminative parts, and deactivate the background regions. Label conditioning imposes that the output label of pseudo-masks should be any of true image-level labels; it penalizes the wrong activation assigned to non-target classes. Based on extensive analysis and evaluations, we demonstrate that each component helps produce accurate pseudo-masks, achieving the robustness against the choice of the global threshold. Finally, our model achieves state-of-the-art records on both PASCAL VOC 2012 and MS COCO 2014 datasets.
Seagrass meadows serve as critical carbon sinks, but estimating the amount of carbon they store requires knowledge of the seagrass species present. Underwater and surface vehicles equipped with machine learning algorithms can help to accurately estimate the composition and extent of seagrass meadows at scale. However, previous approaches for seagrass detection and classification have required supervision from patch-level labels. In this paper, we reframe seagrass classification as a weakly supervised coarse segmentation problem where image-level labels are used during training (25 times fewer labels compared to patch-level labeling) and patch-level outputs are obtained at inference time. To this end, we introduce SeaFeats, an architecture that uses unsupervised contrastive pre-training and feature similarity, and SeaCLIP, a model that showcases the effectiveness of large language models as a supervisory signal in domain-specific applications. We demonstrate that an ensemble of SeaFeats and SeaCLIP leads to highly robust performance. Our method outperforms previous approaches that require patch-level labels on the multi-species 'DeepSeagrass' dataset by 6.8% (absolute) for the class-weighted F1 score, and by 12.1% (absolute) for the seagrass presence/absence F1 score on the 'Global Wetlands' dataset. We also present two case studies for real-world deployment: outlier detection on the Global Wetlands dataset, and application of our method on imagery collected by the FloatyBoat autonomous surface vehicle.
Vision-language pretraining learns rich medical image representations from radiology reports, but previous model variants commonly operate within a single shared embedding space, so concept-level structure and interpretability must be recovered post hoc, limiting model transparency and, hence, clinical utility. We introduce RadPRISM, which makes a clinician-defined radiology schema a designated stratification axis: an on-premise large language model extracts per-concept text spans from free-text reports, and each clinical concept is aligned in its own dedicated visual subspace, turning concept stratification into direct, top-level alignment supervision. Instantiated on chest radiographs with a 19-concept schema over $203{,}602$ examinations from an internal multi-year archive, RadPRISM improved internal dataset zero-shot classification from $0.717$ (95% CI, $0.710-0.723$) to $0.868$ (95% CI, $0.863-0.872$) macro AUROC over a matched global-alignment baseline, performed on par with the purpose-built CARZero reference in external zero-shot classification while substantially outperforming it (up to 4.3-fold) in pointing-game visual grounding. In addition, a radiologist reader study demonstrated concept-stratified retrieval ability ($0.78$ macro retrieval correctness rate within rank 3), surfacing disentangled descriptive findings that report-level retrieval and fixed-label vocabularies cannot express. RadPRISM yields discriminative, spatially faithful, natively concept-stratified representations shaped by and transparently inspectable by clinicians.
Learning the latent representation of data in unsupervised fashion is a very interesting process that provides relevant features for enhancing the performance of a classifier. For speech emotion recognition tasks, generating effective features is crucial. Currently, handcrafted features are mostly used for speech emotion recognition, however, features learned automatically using deep learning have shown strong success in many problems, especially in image processing. In particular, deep generative models such as Variational Autoencoders (VAEs) have gained enormous success for generating features for natural images. Inspired by this, we propose VAEs for deriving the latent representation of speech signals and use this representation to classify emotions. To the best of our knowledge, we are the first to propose VAEs for speech emotion classification. Evaluations on the IEMOCAP dataset demonstrate that features learned by VAEs can produce state-of-the-art results for speech emotion classification.
Computational color constancy refers to the problem of computing the illuminant color so that the images of a scene under varying illumination can be normalized to an image under the canonical illumination. In this paper, we adopt a deep learning framework for the illumination estimation problem. The proposed method works under the assumption of uniform illumination over the scene and aims for the accurate illuminant color computation. Specifically, we trained the convolutional neural network to solve the problem by casting the color constancy problem as an illumination classification problem. We designed the deep learning architecture so that the output of the network can be directly used for computing the color of the illumination. Experimental results show that our deep network is able to extract useful features for the illumination estimation and our method outperforms all previous color constancy methods on multiple test datasets.
The use of orthogonal projections on high-dimensional input and target data in learning frameworks is studied. First, we investigate the relations between two standard objectives in dimension reduction, preservation of variance and of pairwise relative distances. Investigations of their asymptotic correlation as well as numerical experiments show that a projection does usually not satisfy both objectives at once. In a standard classification problem we determine projections on the input data that balance the objectives and compare subsequent results. Next, we extend our application of orthogonal projections to deep learning tasks and introduce a general framework of augmented target loss functions. These loss functions integrate additional information via transformations and projections of the target data. In two supervised learning problems, clinical image segmentation and music information classification, the application of our proposed augmented target loss functions increase the accuracy.
Ultrasound image diagnosis of breast tumors has been widely used in recent years. However, there are some problems of it, for instance, poor quality, intense noise and uneven echo distribution, which has created a huge obstacle to diagnosis. To overcome these problems, we propose a novel method, a breast cancer classification with ultrasound images based on SLIC (BCCUI). We first utilize the Region of Interest (ROI) extraction based on Simple Linear Iterative Clustering (SLIC) algorithm and region growing algorithm to extract the ROI at the super-pixel level. Next, the features of ROI are extracted. Furthermore, the Support Vector Machine (SVM) classifier is applied. The calculation states that the accuracy of this segment algorithm is up to 88.00% and the sensitivity of the algorithm is up to 92.05%, which proves that the classifier presents in this paper has certain research meaning and applied worthiness.