Low-Resource Vision Challenges for Foundation Models

Low-resource settings are well-established in natural language processing, where many languages lack sufficient data for machine learning at scale. However, low-resource problems are under-explored in computer vision. In this paper, we strive to address this gap and explore the challenges of low-resource image tasks with vision foundation models. Thus, we first collect a benchmark of genuinely low-resource image data, covering historic maps, circuit diagrams, and mechanical drawings. These low-resource settings all share the three challenges of data scarcity, fine-grained differences, and the distribution shift from natural images to the specialized domain of interest. While existing foundation models have shown impressive generalizability, we find they cannot transfer well to our low-resource tasks. To begin to tackle the challenges of low-resource vision, we introduce one simple baseline per challenge. Specifically, we propose to i) enlarge the data space by generative models, ii) adopt the best sub-kernels to encode local regions for fine-grained difference discovery and iii) learn attention for specialized domains. Experiments on the three low-resource data sources in our benchmark demonstrate our proposals already provide a better baseline than common transfer learning, data augmentation, and fine-grained methods. This highlights the unique characteristics and challenges of low-resource vision for foundation models that warrant further investigation. Project website: https://xiaobai1217.github.io/Low-Resource-Vision/.

Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discovery

In the quest for unveiling novel categories at test time, we confront the inherent limitations of traditional supervised recognition models that are restricted by a predefined category set. While strides have been made in the realms of self-supervised and open-world learning towards test-time category discovery, a crucial yet often overlooked question persists: what exactly delineates a category? In this paper, we conceptualize a category through the lens of optimization, viewing it as an optimal solution to a well-defined problem. Harnessing this unique conceptualization, we propose a novel, efficient and self-supervised method capable of discovering previously unknown categories at test time. A salient feature of our approach is the assignment of minimum length category codes to individual data instances, which encapsulates the implicit category hierarchy prevalent in real-world datasets. This mechanism affords us enhanced control over category granularity, thereby equipping our model to handle fine-grained categories adeptly. Experimental evaluations, bolstered by state-of-the-art benchmark comparisons, testify to the efficacy of our solution in managing unknown categories at test time. Furthermore, we fortify our proposition with a theoretical foundation, providing proof of its optimality. Our code is available at https://github.com/SarahRastegar/InfoSieve.

Learning Unseen Modality Interaction

Multimodal learning assumes all modality combinations of interest are available during training to learn cross-modal correspondences. In this paper, we challenge this modality-complete assumption for multimodal learning and instead strive for generalization to unseen modality combinations during inference. We pose the problem of unseen modality interaction and introduce a first solution. It exploits a feature projection module to project the multidimensional features of different modalities into a common space with rich information reserved. This allows the information to be accumulated with a simple summation operation across available modalities. To reduce overfitting to unreliable modality combinations during training, we further improve the model learning with pseudo-supervision indicating the reliability of a modality's prediction. We demonstrate that our approach is effective for diverse tasks and modalities by evaluating it for multimodal video classification, robot state regression, and multimedia retrieval.

Tubelet-Contrastive Self-Supervision for Video-Efficient Generalization

We propose a self-supervised method for learning motion-focused video representations. Existing approaches minimize distances between temporally augmented videos, which maintain high spatial similarity. We instead propose to learn similarities between videos with identical local motion dynamics but an otherwise different appearance. We do so by adding synthetic motion trajectories to videos which we refer to as tubelets. By simulating different tubelet motions and applying transformations, such as scaling and rotation, we introduce motion patterns beyond what is present in the pretraining data. This allows us to learn a video representation that is remarkably data-efficient: our approach maintains performance when using only 25% of the pretraining videos. Experiments on 10 diverse downstream settings demonstrate our competitive performance and generalizability to new domains and fine-grained actions.

Day2Dark: Pseudo-Supervised Activity Recognition beyond Silent Daylight

State-of-the-art activity recognizers are effective during the day, but not trustworthy in the dark. The main causes are the distribution shift from the lower color contrast as well as the limited availability of labeled dark videos. Our goal is to recognize activities in the dark as well as in the day. To compensate for the lack of labeled dark videos, we introduce a pseudo-supervised learning scheme, which utilizes task-irrelevant unlabeled dark videos to train an activity recognizer. Our proposed activity recognizer makes use of audio which is invariant to illumination. However, the usefulness of audio and visual features differs according to the illumination. Thus we propose to make our audio-visual recognizer `darkness-aware'. Experiments on EPIC-Kitchens, Kinetics-Sound, and Charades demonstrate that our proposals enable effective activity recognition in the dark and can even improve robustness to occlusions.

Audio-Adaptive Activity Recognition Across Video Domains

This paper strives for activity recognition under domain shift, for example caused by change of scenery or camera viewpoint. The leading approaches reduce the shift in activity appearance by adversarial training and self-supervised learning. Different from these vision-focused works we leverage activity sounds for domain adaptation as they have less variance across domains and can reliably indicate which activities are not happening. We propose an audio-adaptive encoder and associated learning methods that discriminatively adjust the visual feature representation as well as addressing shifts in the semantic distribution. To further eliminate domain-specific features and include domain-invariant activity sounds for recognition, an audio-infused recognizer is proposed, which effectively models the cross-modal interaction across domains. We also introduce the new task of actor shift, with a corresponding audio-visual dataset, to challenge our method with situations where the activity appearance changes dramatically. Experiments on this dataset, EPIC-Kitchens and CharadesEgo show the effectiveness of our approach.

How Severe is Benchmark-Sensitivity in Video Self-Supervised Learning?

Despite the recent success of video self-supervised learning, there is much still to be understood about their generalization capability. In this paper, we investigate how sensitive video self-supervised learning is to the currently used benchmark convention and whether methods generalize beyond the canonical evaluation setting. We do this across four different factors of sensitivity: domain, samples, actions and task. Our comprehensive set of over 500 experiments, which encompasses 7 video datasets, 9 self-supervised methods and 6 video understanding tasks, reveals that current benchmarks in video self-supervised learning are not a good indicator of generalization along these sensitivity factors. Further, we find that self-supervised methods considerably lag behind vanilla supervised pre-training, especially when domain shift is large and the amount of available downstream samples are low. From our analysis we distill the SEVERE-benchmark, a subset of our experiments, and discuss its implication for evaluating the generalizability of representations obtained by existing and future self-supervised video learning methods.

How Do You Do It? Fine-Grained Action Understanding with Pseudo-Adverbs

We aim to understand how actions are performed and identify subtle differences, such as 'fold firmly' vs. 'fold gently'. To this end, we propose a method which recognizes adverbs across different actions. However, such fine-grained annotations are difficult to obtain and their long-tailed nature makes it challenging to recognize adverbs in rare action-adverb compositions. Our approach therefore uses semi-supervised learning with multiple adverb pseudo-labels to leverage videos with only action labels. Combined with adaptive thresholding of these pseudo-adverbs we are able to make efficient use of the available data while tackling the long-tailed distribution. Additionally, we gather adverb annotations for three existing video retrieval datasets, which allows us to introduce the new tasks of recognizing adverbs in unseen action-adverb compositions and unseen domains. Experiments demonstrate the effectiveness of our method, which outperforms prior work in recognizing adverbs and semi-supervised works adapted for adverb recognition. We also show how adverbs can relate fine-grained actions.

Skeleton-Contrastive 3D Action Representation Learning

This paper strives for self-supervised learning of a feature space suitable for skeleton-based action recognition. Our proposal is built upon learning invariances to input skeleton representations and various skeleton augmentations via a noise contrastive estimation. In particular, we propose inter-skeleton contrastive learning, which learns from multiple different input skeleton representations in a cross-contrastive manner. In addition, we contribute several skeleton-specific spatial and temporal augmentations which further encourage the model to learn the spatio-temporal dynamics of skeleton data. By learning similarities between different skeleton representations as well as augmented views of the same sequence, the network is encouraged to learn higher-level semantics of the skeleton data than when only using the augmented views. Our approach achieves state-of-the-art performance for self-supervised learning from skeleton data on the challenging PKU and NTU datasets with multiple downstream tasks, including action recognition, action retrieval and semi-supervised learning. Code is available at https://github.com/fmthoker/skeleton-contrast.

On Semantic Similarity in Video Retrieval

Current video retrieval efforts all found their evaluation on an instance-based assumption, that only a single caption is relevant to a query video and vice versa. We demonstrate that this assumption results in performance comparisons often not indicative of models' retrieval capabilities. We propose a move to semantic similarity video retrieval, where (i) multiple videos/captions can be deemed equally relevant, and their relative ranking does not affect a method's reported performance and (ii) retrieved videos/captions are ranked by their similarity to a query. We propose several proxies to estimate semantic similarities in large-scale retrieval datasets, without additional annotations. Our analysis is performed on three commonly used video retrieval datasets (MSR-VTT, YouCook2 and EPIC-KITCHENS).