Related papers: Detecting Semantic Clones of Unseen Functionality

Anomaly detection aims at identifying deviant samples from the normal data distribution. Contrastive learning has provided a successful way to sample representation that enables effective discrimination on anomalies. However, when…

Deep neural networks have achieved outstanding performance over various tasks, but they have a critical issue: over-confident predictions even for completely unknown samples. Many studies have been proposed to successfully filter out these…

Federated multi-task learning (FMTL) seeks to collaboratively train customized models for users with different tasks while preserving data privacy. Most existing approaches assume model congruity (i.e., the use of fully or partially…

Human perception is routinely assessing the similarity between images, both for decision making and creative thinking. But the underlying cognitive process is not really well understood yet, hence difficult to be mimicked by computer vision…

Semi-supervised learning acts as an effective way to leverage massive unlabeled data. In this paper, we propose a novel training strategy, termed as Semi-supervised Contrastive Learning (SsCL), which combines the well-known contrastive loss…

Worked examples are step-by-step solutions to problems in a specific domain, offered to students to acquire domain-specific problem-solving skills. The effectiveness of worked examples could be enhanced by combining them with…

Code clones can detrimentally impact software maintenance and manually detecting them in very large codebases is impractical. Additionally, automated approaches find detection of Type 3 and Type 4 (inexact) clones very challenging. While…

For anomaly detection (AD), early approaches often train separate models for individual classes, yielding high performance but posing challenges in scalability and resource management. Recent efforts have shifted toward training a single…

Finding the same or similar code snippets in source code is one of fundamental activities in software maintenance. Text-based pattern matching tools such as grep is frequently used for such purpose, but making proper queries for the…

Contrastive vision-language models continue to be the dominant approach for image and text retrieval. Contrastive Language-Image Pre-training (CLIP) trains two neural networks in contrastive manner to align their image and text embeddings…

We address contextualized code retrieval, the search for code snippets helpful to fill gaps in a partial input program. Our approach facilitates a large-scale self-supervised contrastive training by splitting source code randomly into…

Semantic segmentation in autonomous driving predominantly focuses on learning from large-scale data with a closed set of known classes without considering unknown objects. Motivated by safety reasons, we address the video class agnostic…

Recent advances in large-scale code generation models have led to remarkable progress in producing high-quality code. These models are trained in a self-supervised manner on extensive unlabeled code corpora using a decoder-only…

Copy detection, which is a task to determine whether an image is a modified copy of any image in a database, is an unsolved problem. Thus, we addressed copy detection by training convolutional neural networks (CNNs) with contrastive…

Classic clone detection approaches are hardly capable of finding redundant code that has been developed independently, i.e., is not the result of copy&paste. To automatically detect such functionally similar code of independent origin, we…

Multi-task learning (MTL) aims to improve the performance of multiple related prediction tasks by leveraging useful information from them. Due to their flexibility and ability to reduce unknown coefficients substantially, the…

Existing contrastive learning methods rely on pairwise sample contrast $z_x^\top z_{x'}$ to learn data representations, but the learned features often lack clear interpretability from a human perspective. Theoretically, it lacks feature…

Existing Multimodal Large Language Models (MLLMs) process a large number of visual tokens, leading to significant computational costs and inefficiency. Instruction-related visual token compression demonstrates strong task relevance, which…

The adoption of Large Language Models (LLMs) for code generation risks incorporating vulnerable code into software systems. Existing detectors face two critical limitations: a lack of systematic cross-model validation and opaque "black box"…

Predicting human perceptual similarity is a challenging subject of ongoing research. The visual process underlying this aspect of human vision is thought to employ multiple different levels of visual analysis (shapes, objects, texture,…