Related papers: CBM: Curriculum by Masking

Concept Bottleneck Models (CBMs) aim for ante-hoc interpretability by learning a bottleneck layer that predicts interpretable concepts before the decision. State-of-the-art approaches typically select which concepts to learn via human…

We propose to learn a curriculum or a syllabus for supervised learning and deep reinforcement learning with deep neural networks by an attachable deep neural network, called ScreenerNet. Specifically, we learn a weight for each sample by…

Matching individuals across non-overlapping camera networks, known as person re-identification, is a fundamentally challenging problem due to the large visual appearance changes caused by variations of viewpoints, lighting, and occlusion.…

Audio-visual segmentation (AVS) is an emerging task that aims to accurately segment sounding objects based on audio-visual cues. The success of AVS learning systems depends on the effectiveness of cross-modal interaction. Such a requirement…

Curriculum learning is a widely adopted training strategy in natural language processing (NLP), where models are exposed to examples organized by increasing difficulty to enhance learning efficiency and performance. However, most existing…

We present Fast Language-Image Pre-training (FLIP), a simple and more efficient method for training CLIP. Our method randomly masks out and removes a large portion of image patches during training. Masking allows us to learn from more…

Continual Learning (CL) aims to sequentially train models on streams of incoming data that vary in distribution by preserving previous knowledge while adapting to new data. Current CL literature focuses on restricted access to previously…

Scene parsing is a great challenge for real-time semantic segmentation. Although traditional semantic segmentation networks have made remarkable leap-forwards in semantic accuracy, the performance of inference speed is unsatisfactory.…

Concept Bottleneck Models (CBMs) have garnered much attention for their ability to elucidate the prediction process through a human-understandable concept layer. However, most previous studies focused on static scenarios where the data and…

The CLIP model has demonstrated significant advancements in aligning visual and language modalities through large-scale pre-training on image-text pairs, enabling strong zero-shot classification and retrieval capabilities on various…

Continual learning (CL) aims to enable learning systems to acquire new knowledge constantly without forgetting previously learned information. CL faces the challenge of mitigating catastrophic forgetting while maintaining interpretability…

Conventional deep learning models deal with images one-by-one, requiring costly and time-consuming expert labeling in the field of medical imaging, and domain-specific restriction limits model generalizability. Visual in-context learning…

Cross-modal text-molecule retrieval task bridges molecule structures and natural language descriptions. Existing methods predominantly focus on aligning text modality and molecule modality, yet they overlook adaptively adjusting the…

Semi-supervised medical image segmentation (SSMIS) leverages unlabeled data to reduce reliance on manually annotated images. However, current SOTA approaches predominantly focus on foreground-oriented modeling (i.e., segmenting only the…

Masked image modeling (MIM) has achieved promising results on various vision tasks. However, the limited discriminability of learned representation manifests there is still plenty to go for making a stronger vision learner. Towards this…

Instruction tuning is essential for aligning large language models (LLMs) to downstream tasks and commonly relies on large, diverse corpora. However, small, high-quality subsets, known as coresets, can deliver comparable or superior…

Scene recognition is an important research topic in computer vision, while feature extraction is a key step of object recognition. Although classical Restricted Boltzmann machines (RBM) can efficiently represent complicated data, it is hard…

Significant advances have been made in the sampling efficiency of diffusion models and flow matching models, driven by Consistency Distillation (CD), which trains a student model to mimic the output of a teacher model at a later timestep.…

Neural combinatorial optimization (NCO) aims at designing problem-independent and efficient neural network-based strategies for solving combinatorial problems. The field recently experienced growth by successfully adapting architectures…

Concept Bottleneck Models (CBMs) and other concept-based interpretable models show great promise for making AI applications more transparent, which is essential in fields like medicine. Despite their success, we demonstrate that CBMs…