Audio-text retrieval (ATR), which retrieves a relevant caption given an audio clip (A2T) and vice versa (T2A), has recently attracted much research attention. Existing methods typically aggregate information from each modality into a single vector for matching, but this sacrifices local details and can hardly capture intricate relationships within and between modalities. Furthermore, current ATR datasets lack comprehensive alignment information, and simple binary contrastive learning labels overlook the measurement of fine-grained semantic differences between samples. To counter these challenges, we present a novel ATR framework that comprehensively captures the matching relationships of multimodal information from different perspectives and finer granularities. Specifically, a fine-grained alignment method is introduced, achieving a more detail-oriented matching through a multiscale process from local to global levels to capture meticulous cross-modal relationships. In addition, we pioneer the application of cross-modal similarity consistency, leveraging intra-modal similarity relationships as soft supervision to boost more intricate alignment. Extensive experiments validate the effectiveness of our approach, outperforming previous methods by significant margins of at least 3.9% (T2A) / 6.9% (A2T) R@1 on the AudioCaps dataset and 2.9% (T2A) / 5.4% (A2T) R@1 on the Clotho dataset.
Multi-agent perception (MAP) allows autonomous systems to understand complex environments by interpreting data from multiple sources. This paper investigates intermediate collaboration for MAP with a specific focus on exploring "good" properties of collaborative view (i.e., post-collaboration feature) and its underlying relationship to individual views (i.e., pre-collaboration features), which were treated as an opaque procedure by most existing works. We propose a novel framework named CMiMC (Contrastive Mutual Information Maximization for Collaborative Perception) for intermediate collaboration. The core philosophy of CMiMC is to preserve discriminative information of individual views in the collaborative view by maximizing mutual information between pre- and post-collaboration features while enhancing the efficacy of collaborative views by minimizing the loss function of downstream tasks. In particular, we define multi-view mutual information (MVMI) for intermediate collaboration that evaluates correlations between collaborative views and individual views on both global and local scales. We establish CMiMNet based on multi-view contrastive learning to realize estimation and maximization of MVMI, which assists the training of a collaboration encoder for voxel-level feature fusion. We evaluate CMiMC on V2X-Sim 1.0, and it improves the SOTA average precision by 3.08% and 4.44% at 0.5 and 0.7 IoU (Intersection-over-Union) thresholds, respectively. In addition, CMiMC can reduce communication volume to 1/32 while achieving performance comparable to SOTA. Code and Appendix are released at https://github.com/77SWF/CMiMC.
Lifelong person re-identification (LReID) assumes a practical scenario where the model is sequentially trained on continuously incoming datasets while alleviating the catastrophic forgetting in the old datasets. However, not only the training datasets but also the gallery images are incrementally accumulated, that requires a huge amount of computational complexity and storage space to extract the features at the inference phase. In this paper, we address the above mentioned problem by incorporating the backward-compatibility to LReID for the first time. We train the model using the continuously incoming datasets while maintaining the model's compatibility toward the previously trained old models without re-computing the features of the old gallery images. To this end, we devise the cross-model compatibility loss based on the contrastive learning with respect to the replay features across all the old datasets. Moreover, we also develop the knowledge consolidation method based on the part classification to learn the shared representation across different datasets for the backward-compatibility. We suggest a more practical methodology for performance evaluation as well where all the gallery and query images are considered together. Experimental results demonstrate that the proposed method achieves a significantly higher performance of the backward-compatibility compared with the existing methods. It is a promising tool for more practical scenarios of LReID.
User Interface (UI) understanding has been an increasingly popular topic over the last few years. So far, there has been a vast focus solely on web and mobile applications. In this paper, we introduce the harder task of computer UI understanding. With the goal of enabling research in this field, we have generated a dataset with a set of videos where a user is performing a sequence of actions and each image shows the desktop contents at that time point. We also present a framework that is composed of a synthetic sample generation pipeline to augment the dataset with relevant characteristics, and a contrastive learning method to classify images in the videos. We take advantage of the natural conditional, tree-like, relationship of the images' characteristics to regularize the learning of the representations by dealing with multiple partial tasks simultaneously. Experimental results show that the proposed framework outperforms previously proposed hierarchical multi-label contrastive losses in fine-grain UI classification.
We introduce eCLIP, an enhanced version of the CLIP model that integrates expert annotations in the form of radiologist eye-gaze heatmaps. It tackles key challenges in contrastive multi-modal medical imaging analysis, notably data scarcity and the "modality gap" -- a significant disparity between image and text embeddings that diminishes the quality of representations and hampers cross-modal interoperability. eCLIP integrates a heatmap processor and leverages mixup augmentation to efficiently utilize the scarce expert annotations, thus boosting the model's learning effectiveness. eCLIP is designed to be generally applicable to any variant of CLIP without requiring any modifications of the core architecture. Through detailed evaluations across several tasks, including zero-shot inference, linear probing, cross-modal retrieval, and Retrieval Augmented Generation (RAG) of radiology reports using a frozen Large Language Model, eCLIP showcases consistent improvements in embedding quality. The outcomes reveal enhanced alignment and uniformity, affirming eCLIP's capability to harness high-quality annotations for enriched multi-modal analysis in the medical imaging domain.
While the introduction of contrastive learning frameworks in sentence representation learning has significantly contributed to advancements in the field, it still remains unclear whether state-of-the-art sentence embeddings can capture the fine-grained semantics of sentences, particularly when conditioned on specific perspectives. In this paper, we introduce Hyper-CL, an efficient methodology that integrates hypernetworks with contrastive learning to compute conditioned sentence representations. In our proposed approach, the hypernetwork is responsible for transforming pre-computed condition embeddings into corresponding projection layers. This enables the same sentence embeddings to be projected differently according to various conditions. Evaluation on two representative conditioning benchmarks, namely conditional semantic text similarity and knowledge graph completion, demonstrates that Hyper-CL is effective in flexibly conditioning sentence representations, showcasing its computational efficiency at the same time. We also provide a comprehensive analysis of the inner workings of our approach, leading to a better interpretation of its mechanisms.
Identifying highlight moments of raw video materials is crucial for improving the efficiency of editing videos that are pervasive on internet platforms. However, the extensive work of manually labeling footage has created obstacles to applying supervised methods to videos of unseen categories. The absence of an audio modality that contains valuable cues for highlight detection in many videos also makes it difficult to use multimodal strategies. In this paper, we propose a novel model with cross-modal perception for unsupervised highlight detection. The proposed model learns representations with visual-audio level semantics from image-audio pair data via a self-reconstruction task. To achieve unsupervised highlight detection, we investigate the latent representations of the network and propose the representation activation sequence learning (RASL) module with k-point contrastive learning to learn significant representation activations. To connect the visual modality with the audio modality, we use the symmetric contrastive learning (SCL) module to learn the paired visual and audio representations. Furthermore, an auxiliary task of masked feature vector sequence (FVS) reconstruction is simultaneously conducted during pretraining for representation enhancement. During inference, the cross-modal pretrained model can generate representations with paired visual-audio semantics given only the visual modality. The RASL module is used to output the highlight scores. The experimental results show that the proposed framework achieves superior performance compared to other state-of-the-art approaches.
Learning medical visual representations through vision-language pre-training has reached remarkable progress. Despite the promising performance, it still faces challenges, i.e., local alignment lacks interpretability and clinical relevance, and the insufficient internal and external representation learning of image-report pairs. To address these issues, we propose an Anatomical Structure-Guided (ASG) framework. Specifically, we parse raw reports into triplets <anatomical region, finding, existence>, and fully utilize each element as supervision to enhance representation learning. For anatomical region, we design an automatic anatomical region-sentence alignment paradigm in collaboration with radiologists, considering them as the minimum semantic units to explore fine-grained local alignment. For finding and existence, we regard them as image tags, applying an image-tag recognition decoder to associate image features with their respective tags within each sample and constructing soft labels for contrastive learning to improve the semantic association of different image-report pairs. We evaluate the proposed ASG framework on two downstream tasks, including five public benchmarks. Experimental results demonstrate that our method outperforms the state-of-the-art methods.
Human-human communication is like a delicate dance where listeners and speakers concurrently interact to maintain conversational dynamics. Hence, an effective model for generating listener nonverbal behaviors requires understanding the dyadic context and interaction. In this paper, we present an effective framework for creating 3D facial motions in dyadic interactions. Existing work consider a listener as a reactive agent with reflexive behaviors to the speaker's voice and facial motions. The heart of our framework is Dyadic Interaction Modeling (DIM), a pre-training approach that jointly models speakers' and listeners' motions through masking and contrastive learning to learn representations that capture the dyadic context. To enable the generation of non-deterministic behaviors, we encode both listener and speaker motions into discrete latent representations, through VQ-VAE. The pre-trained model is further fine-tuned for motion generation. Extensive experiments demonstrate the superiority of our framework in generating listener motions, establishing a new state-of-the-art according to the quantitative measures capturing the diversity and realism of generated motions. Qualitative results demonstrate the superior capabilities of the proposed approach in generating diverse and realistic expressions, eye blinks and head gestures. The code is available at https://github.com/Boese0601/Dyadic-Interaction-Modeling
Autonomous driving stands as a pivotal domain in computer vision, shaping the future of transportation. Within this paradigm, the backbone of the system plays a crucial role in interpreting the complex environment. However, a notable challenge has been the loss of clear supervision when it comes to Bird's Eye View elements. To address this limitation, we introduce CLIP-BEVFormer, a novel approach that leverages the power of contrastive learning techniques to enhance the multi-view image-derived BEV backbones with ground truth information flow. We conduct extensive experiments on the challenging nuScenes dataset and showcase significant and consistent improvements over the SOTA. Specifically, CLIP-BEVFormer achieves an impressive 8.5\% and 9.2\% enhancement in terms of NDS and mAP, respectively, over the previous best BEV model on the 3D object detection task.
Classical object detectors are incapable of detecting novel class objects that are not encountered before. Regarding this issue, Open-Vocabulary Object Detection (OVOD) is proposed, which aims to detect the objects in the candidate class list. However, current OVOD models are suffering from overfitting on the base classes, heavily relying on the large-scale extra data, and complex training process. To overcome these issues, we propose a novel framework with Meta prompt and Instance Contrastive learning (MIC) schemes. Firstly, we simulate a novel-class-emerging scenario to help the prompt learner that learns class and background prompts generalize to novel classes. Secondly, we design an instance-level contrastive strategy to promote intra-class compactness and inter-class separation, which benefits generalization of the detector to novel class objects. Without using knowledge distillation, ensemble model or extra training data during detector training, our proposed MIC outperforms previous SOTA methods trained with these complex techniques on LVIS. Most importantly, MIC shows great generalization ability on novel classes, e.g., with $+4.3\%$ and $+1.9\% \ \mathrm{AP}$ improvement compared with previous SOTA on COCO and Objects365, respectively.
Self-supervised 3D representation learning aims to learn effective representations from large-scale unlabeled point clouds. Most existing approaches adopt point discrimination as the pretext task, which assigns matched points in two distinct views as positive pairs and unmatched points as negative pairs. However, this approach often results in semantically identical points having dissimilar representations, leading to a high number of false negatives and introducing a "semantic conflict" problem. To address this issue, we propose GroupContrast, a novel approach that combines segment grouping and semantic-aware contrastive learning. Segment grouping partitions points into semantically meaningful regions, which enhances semantic coherence and provides semantic guidance for the subsequent contrastive representation learning. Semantic-aware contrastive learning augments the semantic information extracted from segment grouping and helps to alleviate the issue of "semantic conflict". We conducted extensive experiments on multiple 3D scene understanding tasks. The results demonstrate that GroupContrast learns semantically meaningful representations and achieves promising transfer learning performance.
Constructing a 3D scene capable of accommodating open-ended language queries, is a pivotal pursuit, particularly within the domain of robotics. Such technology facilitates robots in executing object manipulations based on human language directives. To tackle this challenge, some research efforts have been dedicated to the development of language-embedded implicit fields. However, implicit fields (e.g. NeRF) encounter limitations due to the necessity of processing a large number of input views for reconstruction, coupled with their inherent inefficiencies in inference. Thus, we present the GaussianGrasper, which utilizes 3D Gaussian Splatting to explicitly represent the scene as a collection of Gaussian primitives. Our approach takes a limited set of RGB-D views and employs a tile-based splatting technique to create a feature field. In particular, we propose an Efficient Feature Distillation (EFD) module that employs contrastive learning to efficiently and accurately distill language embeddings derived from foundational models. With the reconstructed geometry of the Gaussian field, our method enables the pre-trained grasping model to generate collision-free grasp pose candidates. Furthermore, we propose a normal-guided grasp module to select the best grasp pose. Through comprehensive real-world experiments, we demonstrate that GaussianGrasper enables robots to accurately query and grasp objects with language instructions, providing a new solution for language-guided manipulation tasks. Data and codes can be available at https://github.com/MrSecant/GaussianGrasper.
Recent advancements in self-supervised audio-visual representation learning have demonstrated its potential to capture rich and comprehensive representations. However, despite the advantages of data augmentation verified in many learning methods, audio-visual learning has struggled to fully harness these benefits, as augmentations can easily disrupt the correspondence between input pairs. To address this limitation, we introduce EquiAV, a novel framework that leverages equivariance for audio-visual contrastive learning. Our approach begins with extending equivariance to audio-visual learning, facilitated by a shared attention-based transformation predictor. It enables the aggregation of features from diverse augmentations into a representative embedding, providing robust supervision. Notably, this is achieved with minimal computational overhead. Extensive ablation studies and qualitative results verify the effectiveness of our method. EquiAV outperforms previous works across various audio-visual benchmarks. The code is available on https://github.com/JongSuk1/EquiAV.
Anomaly detection in dynamic graphs presents a significant challenge due to the temporal evolution of graph structures and attributes. The conventional approaches that tackle this problem typically employ an unsupervised learning framework, capturing normality patterns with exclusive normal data during training and identifying deviations as anomalies during testing. However, these methods face critical drawbacks: they either only depend on proxy tasks for representation without directly pinpointing normal patterns, or they neglect to differentiate between spatial and temporal normality patterns. More recent methods that use contrastive learning with negative sampling also face high computational costs, limiting their scalability to large graphs. To address these challenges, we introduce a novel Spatial-Temporal memories-enhanced graph autoencoder (STRIPE). Initially, STRIPE employs Graph Neural Networks (GNNs) and gated temporal convolution layers to extract spatial and temporal features. Then STRIPE incorporates separate spatial and temporal memory networks to capture and store prototypes of normal patterns, respectively. These stored patterns are retrieved and integrated with encoded graph embeddings through a mutual attention mechanism. Finally, the integrated features are fed into the decoder to reconstruct the graph streams which serve as the proxy task for anomaly detection. This comprehensive approach not only minimizes reconstruction errors but also emphasizes the compactness and distinctiveness of the embeddings w.r.t. the nearest memory prototypes. Extensive experiments on six benchmark datasets demonstrate the effectiveness and efficiency of STRIPE, where STRIPE significantly outperforms existing methods with 5.8% improvement in AUC scores and 4.62X faster in training time.
Contrastive pretraining is well-known to improve downstream task performance and model generalisation, especially in limited label settings. However, it is sensitive to the choice of augmentation pipeline. Positive pairs should preserve semantic information while destroying domain-specific information. Standard augmentation pipelines emulate domain-specific changes with pre-defined photometric transformations, but what if we could simulate realistic domain changes instead? In this work, we show how to utilise recent progress in counterfactual image generation to this effect. We propose CF-SimCLR, a counterfactual contrastive learning approach which leverages approximate counterfactual inference for positive pair creation. Comprehensive evaluation across five datasets, on chest radiography and mammography, demonstrates that CF-SimCLR substantially improves robustness to acquisition shift with higher downstream performance on both in- and out-of-distribution data, particularly for domains which are under-represented during training.
Multi-Instance Learning (MIL) has shown impressive performance for histopathology whole slide image (WSI) analysis using bags or pseudo-bags. It involves instance sampling, feature representation, and decision-making. However, existing MIL-based technologies at least suffer from one or more of the following problems: 1) requiring high storage and intensive pre-processing for numerous instances (sampling); 2) potential over-fitting with limited knowledge to predict bag labels (feature representation); 3) pseudo-bag counts and prior biases affect model robustness and generalizability (decision-making). Inspired by clinical diagnostics, using the past sampling instances can facilitate the final WSI analysis, but it is barely explored in prior technologies. To break free these limitations, we integrate the dynamic instance sampling and reinforcement learning into a unified framework to improve the instance selection and feature aggregation, forming a novel Dynamic Policy Instance Selection (DPIS) scheme for better and more credible decision-making. Specifically, the measurement of feature distance and reward function are employed to boost continuous instance sampling. To alleviate the over-fitting, we explore the latent global relations among instances for more robust and discriminative feature representation while establishing reward and punishment mechanisms to correct biases in pseudo-bags using contrastive learning. These strategies form the final Dynamic Policy-Driven Adaptive Multi-Instance Learning (PAMIL) method for WSI tasks. Extensive experiments reveal that our PAMIL method outperforms the state-of-the-art by 3.8\% on CAMELYON16 and 4.4\% on TCGA lung cancer datasets.
In recent times, the focus on text-to-audio (TTA) generation has intensified, as researchers strive to synthesize audio from textual descriptions. However, most existing methods, though leveraging latent diffusion models to learn the correlation between audio and text embeddings, fall short when it comes to maintaining a seamless synchronization between the produced audio and its video. This often results in discernible audio-visual mismatches. To bridge this gap, we introduce a groundbreaking benchmark for Text-to-Audio generation that aligns with Videos, named T2AV-Bench. This benchmark distinguishes itself with three novel metrics dedicated to evaluating visual alignment and temporal consistency. To complement this, we also present a simple yet effective video-aligned TTA generation model, namely T2AV. Moving beyond traditional methods, T2AV refines the latent diffusion approach by integrating visual-aligned text embeddings as its conditional foundation. It employs a temporal multi-head attention transformer to extract and understand temporal nuances from video data, a feat amplified by our Audio-Visual ControlNet that adeptly merges temporal visual representations with text embeddings. Further enhancing this integration, we weave in a contrastive learning objective, designed to ensure that the visual-aligned text embeddings resonate closely with the audio features. Extensive evaluations on the AudioCaps and T2AV-Bench demonstrate that our T2AV sets a new standard for video-aligned TTA generation in ensuring visual alignment and temporal consistency.
Several accounts of human cognition posit that our intelligence is rooted in our ability to form abstract composable concepts, ground them in our environment, and reason over these grounded entities. This trifecta of human thought has remained elusive in modern intelligent machines. In this work, we investigate whether slot representations extracted from visual scenes serve as appropriate compositional abstractions for grounding and reasoning. We present the Neural Slot Interpreter (NSI), which learns to ground object semantics in slots. At the core of NSI is a nested schema that uses simple syntax rules to organize the object semantics of a scene into object-centric schema primitives. Then, the NSI metric learns to ground primitives into slots through a structured contrastive learning objective that reasons over the intermodal alignment. Experiments with a bi-modal object-property and scene retrieval task demonstrate the grounding efficacy and interpretability of correspondences learned by NSI. From a scene representation standpoint, we find that emergent NSI slots that move beyond the image grid by binding to spatial objects facilitate improved visual grounding compared to conventional bounding-box-based approaches. From a data efficiency standpoint, we empirically validate that NSI learns more generalizable representations from a fixed amount of annotation data than the traditional approach. We also show that the grounded slots surpass unsupervised slots in real-world object discovery and scale with scene complexity. Finally, we investigate the downstream efficacy of the grounded slots. Vision Transformers trained on grounding-aware NSI tokenizers using as few as ten tokens outperform patch-based tokens on challenging few-shot classification tasks.
Contrastive learning is a paradigm for learning representations from unlabelled data that has been highly successful for image and text data. Several recent works have examined contrastive losses to claim that contrastive models effectively learn spectral embeddings, while few works show relations between (wide) contrastive models and kernel principal component analysis (PCA). However, it is not known if trained contrastive models indeed correspond to kernel methods or PCA. In this work, we analyze the training dynamics of two-layer contrastive models, with non-linear activation, and answer when these models are close to PCA or kernel methods. It is well known in the supervised setting that neural networks are equivalent to neural tangent kernel (NTK) machines, and that the NTK of infinitely wide networks remains constant during training. We provide the first convergence results of NTK for contrastive losses, and present a nuanced picture: NTK of wide networks remains almost constant for cosine similarity based contrastive losses, but not for losses based on dot product similarity. We further study the training dynamics of contrastive models with orthogonality constraints on output layer, which is implicitly assumed in works relating contrastive learning to spectral embedding. Our deviation bounds suggest that representations learned by contrastive models are close to the principal components of a certain matrix computed from random features. We empirically show that our theoretical results possibly hold beyond two-layer networks.