Shreyank N Gowda

Shreyank N Gowda, Marcus Rohrbach, Frank Keller et al.

We address the problem of data augmentation for video action recognition. Standard augmentation strategies in video are hand-designed and sample the space of possible augmented data points either at random, without knowing which augmented points will be better, or through heuristics. We propose to learn what makes a good video for action recognition and select only high-quality samples for augmentation. In particular, we choose video compositing of a foreground and a background video as the data augmentation process, which results in diverse and realistic new samples. We learn which pairs of videos to augment without having to actually composite them. This reduces the space of possible augmentations, which has two advantages: it saves computational cost and increases the accuracy of the final trained classifier, as the augmented pairs are of higher quality than average. We present experimental results on the entire spectrum of training settings: few-shot, semi-supervised and fully supervised. We observe consistent improvements across all of them over prior work and baselines on Kinetics, UCF101, HMDB51, and achieve a new state-of-the-art on settings with limited data. We see improvements of up to 8.6% in the semi-supervised setting.

Shreyank N Gowda, Laura Sevilla-Lara

Video understanding has long suffered from reliance on large labeled datasets, motivating research into zero-shot learning. Recent progress in language modeling presents opportunities to advance zero-shot video analysis, but constructing an effective semantic space relating action classes remains challenging. We address this by introducing a novel dataset, Stories, which contains rich textual descriptions for diverse action classes extracted from WikiHow articles. For each class, we extract multi-sentence narratives detailing the necessary steps, scenes, objects, and verbs that characterize the action. This contextual data enables modeling of nuanced relationships between actions, paving the way for zero-shot transfer. We also propose an approach that harnesses Stories to improve feature generation for training zero-shot classification. Without any target dataset fine-tuning, our method achieves new state-of-the-art on multiple benchmarks, improving top-1 accuracy by up to 6.1%. We believe Stories provides a valuable resource that can catalyze progress in zero-shot action recognition. The textual narratives forge connections between seen and unseen classes, overcoming the bottleneck of labeled data that has long impeded advancements in this exciting domain. The data can be found here: https://github.com/kini5gowda/Stories .

Shreyank N Gowda, Xinyue Hao, Gen Li et al.

Deep learning models have revolutionized various fields, from image recognition to natural language processing, by achieving unprecedented levels of accuracy. However, their increasing energy consumption has raised concerns about their environmental impact, disadvantaging smaller entities in research and exacerbating global energy consumption. In this paper, we explore the trade-off between model accuracy and electricity consumption, proposing a metric that penalizes large consumption of electricity. We conduct a comprehensive study on the electricity consumption of various deep learning models across different GPUs, presenting a detailed analysis of their accuracy-efficiency trade-offs. By evaluating accuracy per unit of electricity consumed, we demonstrate how smaller, more energy-efficient models can significantly expedite research while mitigating environmental concerns. Our results highlight the potential for a more sustainable approach to deep learning, emphasizing the importance of optimizing models for efficiency. This research also contributes to a more equitable research landscape, where smaller entities can compete effectively with larger counterparts. This advocates for the adoption of efficient deep learning practices to reduce electricity consumption, safeguarding the environment for future generations whilst also helping ensure a fairer competitive landscape.

Shreyank N Gowda, Anurag Arnab, Jonathan Huang

In this paper, we address the challenges posed by the substantial training time and memory consumption associated with video transformers, focusing on the ViViT (Video Vision Transformer) model, in particular the Factorised Encoder version, as our baseline for action recognition tasks. The factorised encoder variant follows the late-fusion approach that is adopted by many state of the art approaches. Despite standing out for its favorable speed/accuracy tradeoffs among the different variants of ViViT, its considerable training time and memory requirements still pose a significant barrier to entry. Our method is designed to lower this barrier and is based on the idea of freezing the spatial transformer during training. This leads to a low accuracy model if naively done. But we show that by (1) appropriately initializing the temporal transformer (a module responsible for processing temporal information) (2) introducing a compact adapter model connecting frozen spatial representations ((a module that selectively focuses on regions of the input image) to the temporal transformer, we can enjoy the benefits of freezing the spatial transformer without sacrificing accuracy. Through extensive experimentation over 6 benchmarks, we demonstrate that our proposed training strategy significantly reduces training costs (by $\sim 50\%$) and memory consumption while maintaining or slightly improving performance by up to 1.79\% compared to the baseline model. Our approach additionally unlocks the capability to utilize larger image transformer models as our spatial transformer and access more frames with the same memory consumption.

Shreyank N Gowda

Generalized Zero-Shot Learning (GZSL) has emerged as a pivotal research domain in computer vision, owing to its capability to recognize objects that have not been seen during training. Despite the significant progress achieved by generative techniques in converting traditional GZSL to fully supervised learning, they tend to generate a large number of synthetic features that are often redundant, thereby increasing training time and decreasing accuracy. To address this issue, this paper proposes a novel approach for synthetic feature selection using reinforcement learning. In particular, we propose a transformer-based selector that is trained through proximal policy optimization (PPO) to select synthetic features based on the validation classification accuracy of the seen classes, which serves as a reward. The proposed method is model-agnostic and data-agnostic, making it applicable to both images and videos and versatile for diverse applications. Our experimental results demonstrate the superiority of our approach over existing feature-generating methods, yielding improved overall performance on multiple benchmarks.

Shreyank N Gowda, David A. Clifton

The Segment Anything Model (SAM) has achieved remarkable successes in the realm of natural image segmentation, but its deployment in the medical imaging sphere has encountered challenges. Specifically, the model struggles with medical images that feature low contrast, faint boundaries, intricate morphologies, and small-sized objects. To address these challenges and enhance SAM's performance in the medical domain, we introduce a comprehensive modification. Firstly, we incorporate a frozen Convolutional Neural Network (CNN) branch as an image encoder, which synergizes with SAM's original Vision Transformer (ViT) encoder through a novel variational attention fusion module. This integration bolsters the model's capability to capture local spatial information, which is often paramount in medical imagery. Moreover, to further optimize SAM for medical imaging, we introduce feature and position adapters within the ViT branch, refining the encoder's representations. We see that compared to current prompting strategies to fine-tune SAM for ultrasound medical segmentation, the use of text descriptions that serve as text prompts for SAM helps significantly improve the performance. Leveraging ChatGPT's natural language understanding capabilities, we generate prompts that offer contextual information and guidance to SAM, enabling it to better understand the nuances of ultrasound medical images and improve its segmentation accuracy. Our method, in its entirety, represents a significant stride towards making universal image segmentation models more adaptable and efficient in the medical domain.

Shreyank N Gowda, Boyan Gao, David A. Clifton

Utilizing large pre-trained models for specific tasks has yielded impressive results. However, fully fine-tuning these increasingly large models is becoming prohibitively resource-intensive. This has led to a focus on more parameter-efficient transfer learning, primarily within the same modality. But this approach has limitations, particularly in video understanding where suitable pre-trained models are less common. Addressing this, our study introduces a novel cross-modality transfer learning approach from images to videos, which we call parameter-efficient image-to-video transfer learning. We present the Facial-Emotion Adapter (FE-Adapter), designed for efficient fine-tuning in video tasks. This adapter allows pre-trained image models, which traditionally lack temporal processing capabilities, to analyze dynamic video content efficiently. Notably, it uses about 15 times fewer parameters than previous methods, while improving accuracy. Our experiments in video emotion recognition demonstrate that the FE-Adapter can match or even surpass existing fine-tuning and video emotion models in both performance and efficiency. This breakthrough highlights the potential for cross-modality approaches in enhancing the capabilities of AI models, particularly in fields like video emotion analysis where the demand for efficiency and accuracy is constantly rising.

Shreyank N Gowda, Dheeraj Pandey, Shashank Narayana Gowda

Recent advancements in deep learning and computer vision have led to a surge of interest in generating realistic talking heads. This paper presents a comprehensive survey of state-of-the-art methods for talking head generation. We systematically categorises them into four main approaches: image-driven, audio-driven, video-driven and others (including neural radiance fields (NeRF), and 3D-based methods). We provide an in-depth analysis of each method, highlighting their unique contributions, strengths, and limitations. Furthermore, we thoroughly compare publicly available models, evaluating them on key aspects such as inference time and human-rated quality of the generated outputs. Our aim is to provide a clear and concise overview of the current landscape in talking head generation, elucidating the relationships between different approaches and identifying promising directions for future research. This survey will serve as a valuable reference for researchers and practitioners interested in this rapidly evolving field.

Zhiyuan Peng, Zihan Ye, Shreyank N Gowda et al.

Zero-shot Learning (ZSL) aims to enable image classifiers to recognize images from unseen classes that were not included during training. Unlike traditional supervised classification, ZSL typically relies on learning a mapping from visual features to predefined, human-understandable class concepts. While ZSL models promise to improve generalization and interpretability, their robustness under systematic input perturbations remain unclear. In this study, we present an empirical analysis about the robustness of existing ZSL methods at both classlevel and concept-level. Specifically, we successfully disrupted their class prediction by the well-known non-target class attack (clsA). However, in the Generalized Zero-shot Learning (GZSL) setting, we observe that the success of clsA is only at the original best-calibrated point. After the attack, the optimal bestcalibration point shifts, and ZSL models maintain relatively strong performance at other calibration points, indicating that clsA results in a spurious attack success in the GZSL. To address this, we propose the Class-Bias Enhanced Attack (CBEA), which completely eliminates GZSL accuracy across all calibrated points by enhancing the gap between seen and unseen class probabilities.Next, at concept-level attack, we introduce two novel attack modes: Class-Preserving Concept Attack (CPconA) and NonClass-Preserving Concept Attack (NCPconA). Our extensive experiments evaluate three typical ZSL models across various architectures from the past three years and reveal that ZSL models are vulnerable not only to the traditional class attack but also to concept-based attacks. These attacks allow malicious actors to easily manipulate class predictions by erasing or introducing concepts. Our findings highlight a significant performance gap between existing approaches, emphasizing the need for improved adversarial robustness in current ZSL models.

Shriram M Sathiyanarayanan, Xinyue Hao, Shihao Hou et al.

The success of the machine learning field has reliably depended on training on large datasets. While effective, this trend comes at an extraordinary cost. This is due to two deeply intertwined factors: the size of models and the size of datasets. While promising research efforts focus on reducing the size of models, the other half of the equation remains fairly mysterious. Indeed, it is surprising that the standard approach to training remains to iterate over and over, uniformly sampling the training dataset. In this paper we explore a series of alternative training paradigms that leverage insights from hard-data-mining and dropout, simple enough to implement and use that can become the new training standard. The proposed Progressive Data Dropout reduces the number of effective epochs to as little as 12.4% of the baseline. This savings actually do not come at any cost for accuracy. Surprisingly, the proposed method improves accuracy by up to 4.82%. Our approach requires no changes to model architecture or optimizer, and can be applied across standard training pipelines, thus posing an excellent opportunity for wide adoption. Code can be found here: https://github.com/bazyagami/LearningWithRevision

Boyan Gao, Bo Zhao, Shreyank N Gowda et al.

Dataset condensation aims to synthesize datasets with a few representative samples that can effectively represent the original datasets. This enables efficient training and produces models with performance close to those trained on the original sets. Most existing dataset condensation methods conduct dataset learning under the bilevel (inner- and outer-loop) based optimization. However, the preceding methods perform with limited dataset generalization due to the notoriously complicated loss landscape and expensive time-space complexity of the inner-loop unrolling of bilevel optimization. These issues deteriorate when the datasets are learned via matching the trajectories of networks trained on the real and synthetic datasets with a long horizon inner-loop. To address these issues, we introduce Sharpness-Aware Trajectory Matching (SATM), which enhances the generalization capability of learned synthetic datasets by optimising the sharpness of the loss landscape and objective simultaneously. Moreover, our approach is coupled with an efficient hypergradient approximation that is mathematically well-supported and straightforward to implement along with controllable computational overhead. Empirical evaluations of SATM demonstrate its effectiveness across various applications, including in-domain benchmarks and out-of-domain settings. Moreover, its easy-to-implement properties afford flexibility, allowing it to integrate with other advanced sharpness-aware minimizers. Our code will be released.

Zihan Ye, Shreyank N. Gowda, Xiaowei Huang et al.

Zero-shot Learning (ZSL) aims to enable classifiers to identify unseen classes. This is typically achieved by generating visual features for unseen classes based on learned visual-semantic correlations from seen classes. However, most current generative approaches heavily rely on having a sufficient number of samples from seen classes. Our study reveals that a scarcity of seen class samples results in a marked decrease in performance across many generative ZSL techniques. We argue, quantify, and empirically demonstrate that this decline is largely attributable to spurious visual-semantic correlations. To address this issue, we introduce ZeroDiff, an innovative generative framework for ZSL that incorporates diffusion mechanisms and contrastive representations to enhance visual-semantic correlations. ZeroDiff comprises three key components: (1) Diffusion augmentation, which naturally transforms limited data into an expanded set of noised data to mitigate generative model overfitting; (2) Supervised-contrastive (SC)-based representations that dynamically characterize each limited sample to support visual feature generation; and (3) Multiple feature discriminators employing a Wasserstein-distance-based mutual learning approach, evaluating generated features from various perspectives, including pre-defined semantics, SC-based representations, and the diffusion process. Extensive experiments on three popular ZSL benchmarks demonstrate that ZeroDiff not only achieves significant improvements over existing ZSL methods but also maintains robust performance even with scarce training data. Our codes are available at https://github.com/FouriYe/ZeroDiff_ICLR25.

Hezhao Liu, Yang Lu, Mengke Li et al.

Semi-supervised learning (SSL) has achieved significant progress by leveraging both labeled data and unlabeled data. Existing SSL methods overlook a common real-world scenario when labeled data is extremely scarce, potentially as limited as a single labeled sample in the dataset. General SSL approaches struggle to train effectively from scratch under such constraints, while methods utilizing pre-trained models often fail to find an optimal balance between leveraging limited labeled data and abundant unlabeled data. To address this challenge, we propose Firstly Adapt, Then catEgorize (FATE), a novel SSL framework tailored for scenarios with extremely limited labeled data. At its core, the two-stage prompt tuning paradigm FATE exploits unlabeled data to compensate for scarce supervision signals, then transfers to downstream tasks. Concretely, FATE first adapts a pre-trained model to the feature distribution of downstream data using volumes of unlabeled samples in an unsupervised manner. It then applies an SSL method specifically designed for pre-trained models to complete the final classification task. FATE is designed to be compatible with both vision and vision-language pre-trained models. Extensive experiments demonstrate that FATE effectively mitigates challenges arising from the scarcity of labeled samples in SSL, achieving an average performance improvement of 33.74% across seven benchmarks compared to state-of-the-art SSL methods. Code is available at https://anonymous.4open.science/r/Semi-supervised-learning-BA72.

Kiyoon Kim, Shreyank N Gowda, Oisin Mac Aodha et al.

We address the problem of capturing temporal information for video classification in 2D networks, without increasing their computational cost. Existing approaches focus on modifying the architecture of 2D networks (e.g. by including filters in the temporal dimension to turn them into 3D networks, or using optical flow, etc.), which increases computation cost. Instead, we propose a novel sampling strategy, where we re-order the channels of the input video, to capture short-term frame-to-frame changes. We observe that without bells and whistles, the proposed sampling strategy improves performance on multiple architectures (e.g. TSN, TRN, TSM, and MVFNet) and datasets (CATER, Something-Something-V1 and V2), up to 24% over the baseline of using the standard video input. In addition, our sampling strategies do not require training from scratch and do not increase the computational cost of training and testing. Given the generality of the results and the flexibility of the approach, we hope this can be widely useful to the video understanding community. Code is available on our website: https://github.com/kiyoon/channel_sampling.

Shreyank N Gowda, Davide Moltisanti, Laura Sevilla-Lara

Zero-shot action recognition requires a strong ability to generalize from pre-training and seen classes to novel unseen classes. Similarly, continual learning aims to develop models that can generalize effectively and learn new tasks without forgetting the ones previously learned. The generalization goals of zero-shot and continual learning are closely aligned, however techniques from continual learning have not been applied to zero-shot action recognition. In this paper, we propose a novel method based on continual learning to address zero-shot action recognition. This model, which we call {\em Generative Iterative Learning} (GIL) uses a memory of synthesized features of past classes, and combines these synthetic features with real ones from novel classes. The memory is used to train a classification model, ensuring a balanced exposure to both old and new classes. Experiments demonstrate that {\em GIL} improves generalization in unseen classes, achieving a new state-of-the-art in zero-shot recognition across multiple benchmarks. Importantly, {\em GIL} also boosts performance in the more challenging generalized zero-shot setting, where models need to retain knowledge about classes seen before fine-tuning.

Zihan Ye, Shreyank N Gowda, Shiming Chen et al.

Zero-shot learning (ZSL) aims to recognize unseen classes by aligning images with intermediate class semantics, like human-annotated concepts or class definitions. An emerging alternative leverages Large-scale Language Models (LLMs) to automatically generate class documents. However, these methods often face challenges with transparency in the classification process and may suffer from the notorious hallucination problem in LLMs, resulting in non-visual class semantics. This paper redefines class semantics in ZSL with a focus on transferability and discriminability, introducing a novel framework called Zero-shot Learning with Infinite Class Concepts (InfZSL). Our approach leverages the powerful capabilities of LLMs to dynamically generate an unlimited array of phrase-level class concepts. To address the hallucination challenge, we introduce an entropy-based scoring process that incorporates a ``goodness" concept selection mechanism, ensuring that only the most transferable and discriminative concepts are selected. Our InfZSL framework not only demonstrates significant improvements on three popular benchmark datasets but also generates highly interpretable, image-grounded concepts. Code will be released upon acceptance.

Zhiying Li, Zhi Liu, Guanggang Geng et al.

Object detectors, which are widely used in real-world applications, are vulnerable to backdoor attacks. This vulnerability arises because many users rely on datasets or pre-trained models provided by third parties due to constraints on data and resources. However, most research on backdoor attacks has focused on image classification, with limited investigation into object detection. Furthermore, the triggers for most existing backdoor attacks on object detection are manually generated, requiring prior knowledge and consistent patterns between the training and inference stages. This approach makes the attacks either easy to detect or difficult to adapt to various scenarios. To address these limitations, we propose novel twin trigger generative networks in the frequency domain to generate invisible triggers for implanting stealthy backdoors into models during training, and visible triggers for steady activation during inference, making the attack process difficult to trace. Specifically, for the invisible trigger generative network, we deploy a Gaussian smoothing layer and a high-frequency artifact classifier to enhance the stealthiness of backdoor implantation in object detectors. For the visible trigger generative network, we design a novel alignment loss to optimize the visible triggers so that they differ from the original patterns but still align with the malicious activation behavior of the invisible triggers. Extensive experimental results and analyses prove the possibility of using different triggers in the training stage and the inference stage, and demonstrate the attack effectiveness of our proposed visible trigger and invisible trigger generative networks, significantly reducing the mAP_0.5 of the object detectors by 70.0% and 84.5%, including YOLOv5 and YOLOv7 with different settings, respectively.

Xiang Li, Chong Zhang, Hongpeng Wang et al.

This work focuses on the high carbon emissions generated by deep learning model training, specifically addressing the core challenge of balancing algorithm performance and energy consumption. It proposes an innovative two-dimensional sustainability evaluation system. Different from the traditional single performance-oriented evaluation paradigm, this study pioneered two quantitative indicators that integrate energy efficiency ratio and accuracy: the sustainable harmonic mean (FMS) integrates accumulated energy consumption and performance parameters through the harmonic mean to reveal the algorithm performance under unit energy consumption; the area under the sustainability curve (ASC) constructs a performance-power consumption curve to characterize the energy efficiency characteristics of the algorithm throughout the cycle. To verify the universality of the indicator system, the study constructed benchmarks in various multimodal tasks, including image classification, segmentation, pose estimation, and batch and online learning. Experiments demonstrate that the system can provide a quantitative basis for evaluating cross-task algorithms and promote the transition of green AI research from theory to practice. Our sustainability evaluation framework code can be found here, providing methodological support for the industry to establish algorithm energy efficiency standards.

Xiao Gu, Wei Tang, Jinpei Han et al. · oxford

Cardiac biosignals, such as electrocardiograms (ECG) and photoplethysmograms (PPG), are of paramount importance for the diagnosis, prevention, and management of cardiovascular diseases, and have been extensively used in a variety of clinical tasks. Conventional deep learning approaches for analyzing these signals typically rely on homogeneous datasets and static bespoke models, limiting their robustness and generalizability across diverse clinical settings and acquisition protocols. In this study, we present a cardiac sensing foundation model (CSFM) that leverages advanced transformer architectures and a generative, masked pretraining strategy to learn unified representations from vast, heterogeneous health records. Our model is pretrained on an innovative multi-modal integration of data from multiple large-scale datasets (including MIMIC-III-WDB, MIMIC-IV-ECG, and CODE), comprising cardiac signals and the corresponding clinical or machine-generated text reports from approximately 1.7 million individuals. We demonstrate that the embeddings derived from our CSFM not only serve as effective feature extractors across diverse cardiac sensing scenarios, but also enable seamless transfer learning across varying input configurations and sensor modalities. Extensive evaluations across diagnostic tasks, demographic information recognition, vital sign measurement, clinical outcome prediction, and ECG question answering reveal that CSFM consistently outperforms traditional one-modal-one-task approaches. Notably, CSFM exhibits robust performance across multiple ECG lead configurations from standard 12-lead systems to single-lead setups, and in scenarios where only ECG, only PPG, or a combination thereof is available. These findings highlight the potential of CSFM as a versatile and scalable solution, for comprehensive cardiac monitoring.

Shreyank N Gowda, Boyan Gao, Xiao Gu et al.

Video understanding has shown remarkable improvements in recent years, largely dependent on the availability of large scaled labeled datasets. Recent advancements in visual-language models, especially based on contrastive pretraining, have shown remarkable generalization in zero-shot tasks, helping to overcome this dependence on labeled datasets. Adaptations of such models for videos, typically involve modifying the architecture of vision-language models to cater to video data. However, this is not trivial, since such adaptations are mostly computationally intensive and struggle with temporal modeling. We present TP-CLIP, an adaptation of CLIP that leverages temporal visual prompting for temporal adaptation without modifying the core CLIP architecture. This preserves its generalization abilities. TP-CLIP efficiently integrates into the CLIP architecture, leveraging its pre-trained capabilities for video data. Extensive experiments across various datasets demonstrate its efficacy in zero-shot and few-shot learning, outperforming existing approaches with fewer parameters and computational efficiency. In particular, we use just 1/3 the GFLOPs and 1/28 the number of tuneable parameters in comparison to recent state-of-the-art and still outperform it by up to 15.8% depending on the task and dataset.

Xinyue Hao, Gen Li, Shreyank N Gowda et al.

Video understanding has made huge strides in recent years, relying largely on the power of transformers. As this architecture is notoriously expensive and video data is highly redundant, research into improving efficiency has become particularly relevant. Some creative solutions include token selection and merging. While most methods succeed in reducing the cost of the model and maintaining accuracy, an interesting pattern arises: most methods do not outperform the baseline of randomly discarding tokens. In this paper we take a closer look at this phenomenon and observe 5 principles of the nature of visual tokens. For example, we observe that the value of tokens follows a clear Pareto-distribution where most tokens have remarkably low value, and just a few carry most of the perceptual information. We build on these and further insights to propose a lightweight video model, LITE, that can select a small number of tokens effectively, outperforming state-of-the-art and existing baselines across datasets (Kinetics-400 and Something-Something-V2) in the challenging trade-off of computation (GFLOPs) vs accuracy. Experiments also show that LITE generalizes across datasets and even other tasks without the need for retraining.

Shreyank N Gowda, Yash Thakre, Shashank Narayana Gowda et al.

This paper offers a comprehensive analysis of recent advancements in video inpainting techniques, a critical subset of computer vision and artificial intelligence. As a process that restores or fills in missing or corrupted portions of video sequences with plausible content, video inpainting has evolved significantly with the advent of deep learning methodologies. Despite the plethora of existing methods and their swift development, the landscape remains complex, posing challenges to both novices and established researchers. Our study deconstructs major techniques, their underpinning theories, and their effective applications. Moreover, we conduct an exhaustive comparative study, centering on two often-overlooked dimensions: visual quality and computational efficiency. We adopt a human-centric approach to assess visual quality, enlisting a panel of annotators to evaluate the output of different video inpainting techniques. This provides a nuanced qualitative understanding that complements traditional quantitative metrics. Concurrently, we delve into the computational aspects, comparing inference times and memory demands across a standardized hardware setup. This analysis underscores the balance between quality and efficiency: a critical consideration for practical applications where resources may be constrained. By integrating human validation and computational resource comparison, this survey not only clarifies the present landscape of video inpainting techniques but also charts a course for future explorations in this vibrant and evolving field.

Kiyoon Kim, Shreyank N Gowda, Panagiotis Eustratiadis et al.

Despite recent advances in video action recognition achieving strong performance on existing benchmarks, these models often lack robustness when faced with natural distribution shifts between training and test data. We propose two novel evaluation methods to assess model resilience to such distribution disparity. One method uses two different datasets collected from different sources and uses one for training and validation, and the other for testing. More precisely, we created dataset splits of HMDB-51 or UCF-101 for training, and Kinetics-400 for testing, using the subset of the classes that are overlapping in both train and test datasets. The other proposed method extracts the feature mean of each class from the target evaluation dataset's training data (i.e. class prototype) and estimates test video prediction as a cosine similarity score between each sample to the class prototypes of each target class. This procedure does not alter model weights using the target dataset and it does not require aligning overlapping classes of two different datasets, thus is a very efficient method to test the model robustness to distribution shifts without prior knowledge of the target distribution. We address the robustness problem by adversarial augmentation training - generating augmented views of videos that are "hard" for the classification model by applying gradient ascent on the augmentation parameters - as well as "curriculum" scheduling the strength of the video augmentations. We experimentally demonstrate the superior performance of the proposed adversarial augmentation approach over baselines across three state-of-the-art action recognition models - TSM, Video Swin Transformer, and Uniformer. The presented work provides critical insight into model robustness to distribution shifts and presents effective techniques to enhance video action recognition performance in a real-world deployment.

Shreyank N Gowda, Laura Sevilla-Lara, Kiyoon Kim et al.

Zero-shot action recognition is the task of classifying action categories that are not available in the training set. In this setting, the standard evaluation protocol is to use existing action recognition datasets(e.g. UCF101) and randomly split the classes into seen and unseen. However, most recent work builds on representations pre-trained on the Kinetics dataset, where classes largely overlap with classes in the zero-shot evaluation datasets. As a result, classes which are supposed to be unseen, are present during supervised pre-training, invalidating the condition of the zero-shot setting. A similar concern was previously noted several years ago for image based zero-shot recognition but has not been considered by the zero-shot action recognition community. In this paper, we propose a new split for true zero-shot action recognition with no overlap between unseen test classes and training or pre-training classes. We benchmark several recent approaches on the proposed True Zero-Shot(TruZe) Split for UCF101 and HMDB51, with zero-shot and generalized zero-shot evaluation. In our extensive analysis, we find that our TruZesplits are significantly harder than comparable random splits as nothing is leaking from pre-training, i.e. unseen performance is consistently lower,up to 8.9% for zero-shot action recognition. In an additional evaluation we also find that similar issues exist in the splits used in few-shot action recognition, here we see differences of up to 17.1%. We publish oursplits1and hope that our benchmark analysis will change how the field is evaluating zero- and few-shot action recognition moving forward.

Liam Wellacott, Emilyann Nault, Ioannis Skottis et al.

Virtual environments have been utilised in robotics research as a tool to assess systems before deploying them in the field. The COVID-19 pandemic has brought about additional motivation for the development of virtual benchmarks in order to aid in safe and productive development. In-person robotics competitions have also halted, thus limiting the scope of opportunities for students and researchers. We implemented the structure of a service robotics competition into an extendable and adaptable virtual scoring environment. The competition challenges the state of the art in home service robotics by presenting realistic household tasks for robots to complete. The virtual environment provides a foundation for competition teams to assess their systems when accessing the physical environment is not possible. We believe that utilising virtual environments as a means of assessment will lead to other benefits such as increased access and generalisation.

Shreyank N Gowda, Laura Sevilla-Lara, Frank Keller et al.

Zero-shot action recognition is the task of recognizingaction classes without visual examples, only with a seman-tic embedding which relates unseen to seen classes. Theproblem can be seen as learning a function which general-izes well to instances of unseen classes without losing dis-crimination between classes. Neural networks can modelthe complex boundaries between visual classes, which ex-plains their success as supervised models. However, inzero-shot learning, these highly specialized class bound-aries may not transfer well from seen to unseen classes.In this paper we propose a centroid-based representation,which clusters visual and semantic representation, consid-ers all training samples at once, and in this way generaliz-ing well to instances from unseen classes. We optimize theclustering using Reinforcement Learning which we show iscritical for our approach to work. We call the proposedmethod CLASTER and observe that it consistently outper-forms the state-of-the-art in all standard datasets, includ-ing UCF101, HMDB51 and Olympic Sports; both in thestandard zero-shot evaluation and the generalized zero-shotlearning. Further, we show that our model performs com-petitively in the image domain as well, outperforming thestate-of-the-art in many settings.

Shreyank N Gowda, Marcus Rohrbach, Laura Sevilla-Lara

Action recognition is computationally expensive. In this paper, we address the problem of frame selection to improve the accuracy of action recognition. In particular, we show that selecting good frames helps in action recognition performance even in the trimmed videos domain. Recent work has successfully leveraged frame selection for long, untrimmed videos, where much of the content is not relevant, and easy to discard. In this work, however, we focus on the more standard short, trimmed action recognition problem. We argue that good frame selection can not only reduce the computational cost of action recognition but also increase the accuracy by getting rid of frames that are hard to classify. In contrast to previous work, we propose a method that instead of selecting frames by considering one at a time, considers them jointly. This results in a more efficient selection, where good frames are more effectively distributed over the video, like snapshots that tell a story. We call the proposed frame selection SMART and we test it in combination with different backbone architectures and on multiple benchmarks (Kinetics, Something-something, UCF101). We show that the SMART frame selection consistently improves the accuracy compared to other frame selection strategies while reducing the computational cost by a factor of 4 to 10 times. Additionally, we show that when the primary goal is recognition performance, our selection strategy can improve over recent state-of-the-art models and frame selection strategies on various benchmarks (UCF101, HMDB51, FCVID, and ActivityNet).

Shreyank N Gowda, Panagiotis Eustratiadis, Timothy Hospedales et al.

We consider the challenging problem of zero-shot video object segmentation (VOS). That is, segmenting and tracking multiple moving objects within a video fully automatically, without any manual initialization. We treat this as a grouping problem by exploiting object proposals and making a joint inference about grouping over both space and time. We propose a network architecture for tractably performing proposal selection and joint grouping. Crucially, we then show how to train this network with reinforcement learning so that it learns to perform the optimal non-myopic sequence of grouping decisions to segment the whole video. Unlike standard supervised techniques, this also enables us to directly optimize for the non-differentiable overlap-based metrics used to evaluate VOS. We show that the proposed method, which we call ALBA outperforms the previous stateof-the-art on three benchmarks: DAVIS 2017 [2], FBMS [20] and Youtube-VOS [27].

Shreyank N Gowda, Chun Yuan

Minute pixel changes in an image drastically change the prediction that the deep learning model makes. One of the most significant problems that could arise due to this, for instance, is autonomous driving. Many methods have been proposed to combat this with varying amounts of success. We propose a 3 step method for defending such attacks. First, we denoise the image using statistical methods. Second, we show that adopting multiple color spaces in the same model can help us to fight these adversarial attacks further as each color space detects certain features explicit to itself. Finally, the feature maps generated are enlarged and sent back as an input to obtain even smaller features. We show that the proposed model does not need to be trained to defend an particular type of attack and is inherently more robust to black-box, white-box, and grey-box adversarial attack techniques. In particular, the model is 56.12 percent more robust than compared models in case of white box attacks when the models are not subject to adversarial example training.

Shreyank Narayana Gowda

Colorization is the method of converting an image in grayscale to a fully color image. There are multiple methods to do the same. Old school methods used machine learning algorithms and optimization techniques to suggest possible colors to use. With advances in the field of deep learning, colorization results have improved consistently with improvements in deep learning architectures. The latest development in the field of deep learning is the emergence of generative adversarial networks (GANs) which is used to generate information and not just predict or classify. As part of this report, 2 architectures of recent papers are reproduced along with a novel architecture being suggested for general colorization. Following this, we propose the use of colorization by generating makeup suggestions automatically on a face. To do this, a dataset consisting of 1000 images has been created. When an image of a person without makeup is sent to the model, the model first converts the image to grayscale and then passes it through the suggested GAN model. The output is a generated makeup suggestion. To develop this model, we need to tweak the general colorization model to deal only with faces of people.

Shreyank N Gowda, Chun Yuan

Image classification is a fundamental application in computer vision. Recently, deeper networks and highly connected networks have shown state of the art performance for image classification tasks. Most datasets these days consist of a finite number of color images. These color images are taken as input in the form of RGB images and classification is done without modifying them. We explore the importance of color spaces and show that color spaces (essentially transformations of original RGB images) can significantly affect classification accuracy. Further, we show that certain classes of images are better represented in particular color spaces and for a dataset with a highly varying number of classes such as CIFAR and Imagenet, using a model that considers multiple color spaces within the same model gives excellent levels of accuracy. Also, we show that such a model, where the input is preprocessed into multiple color spaces simultaneously, needs far fewer parameters to obtain high accuracy for classification. For example, our model with 1.75M parameters significantly outperforms DenseNet 100-12 that has 12M parameters and gives results comparable to Densenet-BC-190-40 that has 25.6M parameters for classification of four competitive image classification datasets namely: CIFAR-10, CIFAR-100, SVHN and Imagenet. Our model essentially takes an RGB image as input, simultaneously converts the image into 7 different color spaces and uses these as inputs to individual densenets. We use small and wide densenets to reduce computation overhead and number of hyperparameters required. We obtain significant improvement on current state of the art results on these datasets as well.