A streamlined Approach to Multimodal Few-Shot Class Incremental Learning for Fine-Grained Datasets

Few-shot Class-Incremental Learning (FSCIL) poses the challenge of retaining prior knowledge while learning from limited new data streams, all without overfitting. The rise of Vision-Language models (VLMs) has unlocked numerous applications, leveraging their existing knowledge to fine-tune on custom data. However, training the whole model is computationally prohibitive, and VLMs while being versatile in general domains still struggle with fine-grained datasets crucial for many applications. We tackle these challenges with two proposed simple modules. The first, Session-Specific Prompts (SSP), enhances the separability of image-text embeddings across sessions. The second, Hyperbolic distance, compresses representations of image-text pairs within the same class while expanding those from different classes, leading to better representations. Experimental results demonstrate an average 10-point increase compared to baselines while requiring at least 8 times fewer trainable parameters. This improvement is further underscored on our three newly introduced fine-grained datasets.

AttributionScanner: A Visual Analytics System for Metadata-Free Data-Slicing Based Model Validation

Data slice-finding is an emerging technique for evaluating machine learning models. It works by identifying subgroups within a specified dataset that exhibit poor performance, often defined by distinct feature sets or meta-information. However, in the context of unstructured image data, data slice-finding poses two notable challenges: it requires additional metadata -- a laborious and costly requirement, and also demands non-trivial efforts for interpreting the root causes of the underperformance within data slices. To address these challenges, we introduce AttributionScanner, an innovative human-in-the-loop Visual Analytics (VA) system, designed for data-slicing-based machine learning (ML) model validation. Our approach excels in identifying interpretable data slices, employing explainable features extracted through the lens of Explainable AI (XAI) techniques, and removing the necessity for additional metadata of textual annotations or cross-model embeddings. AttributionScanner demonstrates proficiency in pinpointing critical model issues, including spurious correlations and mislabeled data. Our novel VA interface visually summarizes data slices, enabling users to gather insights into model behavior patterns effortlessly. Furthermore, our framework closes the ML Development Cycle by empowering domain experts to address model issues by using a cutting-edge neural network regularization technique. The efficacy of AttributionScanner is underscored through two prototype use cases, elucidating its substantial effectiveness in model validation for vision-centric tasks. Our approach paves the way for ML researchers and practitioners to drive interpretable model validation in a data-efficient way, ultimately leading to more reliable and accurate models.

InterVLS: Interactive Model Understanding and Improvement with Vision-Language Surrogates

Deep learning models are widely used in critical applications, highlighting the need for pre-deployment model understanding and improvement. Visual concept-based methods, while increasingly used for this purpose, face challenges: (1) most concepts lack interpretability, (2) existing methods require model knowledge, often unavailable at run time. Additionally, (3) there lacks a no-code method for post-understanding model improvement. Addressing these, we present InterVLS. The system facilitates model understanding by discovering text-aligned concepts, measuring their influence with model-agnostic linear surrogates. Employing visual analytics, InterVLS offers concept-based explanations and performance insights. It enables users to adjust concept influences to update a model, facilitating no-code model improvement. We evaluate InterVLS in a user study, illustrating its functionality with two scenarios. Results indicates that InterVLS is effective to help users identify influential concepts to a model, gain insights and adjust concept influence to improve the model. We conclude with a discussion based on our study results.

GradOrth: A Simple yet Efficient Out-of-Distribution Detection with Orthogonal Projection of Gradients

Detecting out-of-distribution (OOD) data is crucial for ensuring the safe deployment of machine learning models in real-world applications. However, existing OOD detection approaches primarily rely on the feature maps or the full gradient space information to derive OOD scores neglecting the role of most important parameters of the pre-trained network over in-distribution (ID) data. In this study, we propose a novel approach called GradOrth to facilitate OOD detection based on one intriguing observation that the important features to identify OOD data lie in the lower-rank subspace of in-distribution (ID) data. In particular, we identify OOD data by computing the norm of gradient projection on the subspaces considered important for the in-distribution data. A large orthogonal projection value (i.e. a small projection value) indicates the sample as OOD as it captures a weak correlation of the ID data. This simple yet effective method exhibits outstanding performance, showcasing a notable reduction in the average false positive rate at a 95% true positive rate (FPR95) of up to 8% when compared to the current state-of-the-art methods.

UP-DP: Unsupervised Prompt Learning for Data Pre-Selection with Vision-Language Models

In this study, we investigate the task of data pre-selection, which aims to select instances for labeling from an unlabeled dataset through a single pass, thereby optimizing performance for undefined downstream tasks with a limited annotation budget. Previous approaches to data pre-selection relied solely on visual features extracted from foundation models, such as CLIP and BLIP-2, but largely ignored the powerfulness of text features. In this work, we argue that, with proper design, the joint feature space of both vision and text can yield a better representation for data pre-selection. To this end, we introduce UP-DP, a simple yet effective unsupervised prompt learning approach that adapts vision-language models, like BLIP-2, for data pre-selection. Specifically, with the BLIP-2 parameters frozen, we train text prompts to extract the joint features with improved representation, ensuring a diverse cluster structure that covers the entire dataset. We extensively compare our method with the state-of-the-art using seven benchmark datasets in different settings, achieving up to a performance gain of 20%. Interestingly, the prompts learned from one dataset demonstrate significant generalizability and can be applied directly to enhance the feature extraction of BLIP-2 from other datasets. To the best of our knowledge, UP-DP is the first work to incorporate unsupervised prompt learning in a vision-language model for data pre-selection.

Hyp-OW: Exploiting Hierarchical Structure Learning with Hyperbolic Distance Enhances Open World Object Detection

Open World Object Detection (OWOD) is a challenging and realistic task that extends beyond the scope of standard Object Detection task. It involves detecting both known and unknown objects while integrating learned knowledge for future tasks. However, the level of 'unknownness' varies significantly depending on the context. For example, a tree is typically considered part of the background in a self-driving scene, but it may be significant in a household context. We argue that this external or contextual information should already be embedded within the known classes. In other words, there should be a semantic or latent structure relationship between the known and unknown items to be discovered. Motivated by this observation, we propose Hyp-OW, a method that learns and models hierarchical representation of known items through a SuperClass Regularizer. Leveraging this learned representation allows us to effectively detect unknown objects using a Similarity Distance-based Relabeling module. Extensive experiments on benchmark datasets demonstrate the effectiveness of Hyp-OW achieving improvement in both known and unknown detection (up to 6 points). These findings are particularly pronounced in our newly designed benchmark, where a strong hierarchical structure exists between known and unknown objects.

CLIP-S$^4$: Language-Guided Self-Supervised Semantic Segmentation

Existing semantic segmentation approaches are often limited by costly pixel-wise annotations and predefined classes. In this work, we present CLIP-S$^4$ that leverages self-supervised pixel representation learning and vision-language models to enable various semantic segmentation tasks (e.g., unsupervised, transfer learning, language-driven segmentation) without any human annotations and unknown class information. We first learn pixel embeddings with pixel-segment contrastive learning from different augmented views of images. To further improve the pixel embeddings and enable language-driven semantic segmentation, we design two types of consistency guided by vision-language models: 1) embedding consistency, aligning our pixel embeddings to the joint feature space of a pre-trained vision-language model, CLIP; and 2) semantic consistency, forcing our model to make the same predictions as CLIP over a set of carefully designed target classes with both known and unknown prototypes. Thus, CLIP-S$^4$ enables a new task of class-free semantic segmentation where no unknown class information is needed during training. As a result, our approach shows consistent and substantial performance improvement over four popular benchmarks compared with the state-of-the-art unsupervised and language-driven semantic segmentation methods. More importantly, our method outperforms these methods on unknown class recognition by a large margin.

Self-supervised Semantic Segmentation Grounded in Visual Concepts

Unsupervised semantic segmentation requires assigning a label to every pixel without any human annotations. Despite recent advances in self-supervised representation learning for individual images, unsupervised semantic segmentation with pixel-level representations is still a challenging task and remains underexplored. In this work, we propose a self-supervised pixel representation learning method for semantic segmentation by using visual concepts (i.e., groups of pixels with semantic meanings, such as parts, objects, and scenes) extracted from images. To guide self-supervised learning, we leverage three types of relationships between pixels and concepts, including the relationships between pixels and local concepts, local and global concepts, as well as the co-occurrence of concepts. We evaluate the learned pixel embeddings and visual concepts on three datasets, including PASCAL VOC 2012, COCO 2017, and DAVIS 2017. Our results show that the proposed method gains consistent and substantial improvements over recent unsupervised semantic segmentation approaches, and also demonstrate that visual concepts can reveal insights into image datasets.

Novelty-based Generalization Evaluation for Traffic Light Detection

The advent of Convolutional Neural Networks (CNNs) has led to their application in several domains. One noteworthy application is the perception system for autonomous driving that relies on the predictions from CNNs. Practitioners evaluate the generalization ability of such CNNs by calculating various metrics on an independent test dataset. A test dataset is often chosen based on only one precondition, i.e., its elements are not a part of the training data. Such a dataset may contain objects that are both similar and novel w.r.t. the training dataset. Nevertheless, existing works do not reckon the novelty of the test samples and treat them all equally for evaluating generalization. Such novelty-based evaluations are of significance to validate the fitness of a CNN in autonomous driving applications. Hence, we propose a CNN generalization scoring framework that considers novelty of objects in the test dataset. We begin with the representation learning technique to reduce the image data into a low-dimensional space. It is on this space we estimate the novelty of the test samples. Finally, we calculate the generalization score as a combination of the test data prediction performance and novelty. We perform an experimental study of the same for our traffic light detection application. In addition, we systematically visualize the results for an interpretable notion of novelty.

VATLD: A Visual Analytics System to Assess, Understand and Improve Traffic Light Detection

Traffic light detection is crucial for environment perception and decision-making in autonomous driving. State-of-the-art detectors are built upon deep Convolutional Neural Networks (CNNs) and have exhibited promising performance. However, one looming concern with CNN based detectors is how to thoroughly evaluate the performance of accuracy and robustness before they can be deployed to autonomous vehicles. In this work, we propose a visual analytics system, VATLD, equipped with a disentangled representation learning and semantic adversarial learning, to assess, understand, and improve the accuracy and robustness of traffic light detectors in autonomous driving applications. The disentangled representation learning extracts data semantics to augment human cognition with human-friendly visual summarization, and the semantic adversarial learning efficiently exposes interpretable robustness risks and enables minimal human interaction for actionable insights. We also demonstrate the effectiveness of various performance improvement strategies derived from actionable insights with our visual analytics system, VATLD, and illustrate some practical implications for safety-critical applications in autonomous driving.