#image classification

try —

13 papers match

cs.AI2026

A Fuzzy Rule-based Neuro-Symbolic Approach for Pipe Severity Prediction in Sewer Networks

Ngoc Thai Le, Thanh Ma, Umberto Straccia

The paper presents a modular neuro‑symbolic system that uses a Swin Transformer to predict multilabel pipe defect codes from images and then applies fuzzy IF‑THEN rules derived fro…

#sewer pipe inspection#neuro-symbolic reasoning#fuzzy logic#image classification
cs.LG2026

Kohn-Sham Spectral Embedding on Sparse Graphs at the Nishimori Temperature for Image Classification

V. S. Usatyuk, D. A. Sapozhnikov, S. I. Egorov

The paper proposes Kohn‑Sham Spectral Embedding (KSSE), a physics‑inspired, sparse‑graph spectral method that replaces dense CNN classifiers with a regularized Laplacian evaluated…

#spectral embedding#sparse graphs#energy-based models#image classification
cs.LG2026

Contrastive Concept Importance: Explaining Pairwise Class Decisions Through Automatically Extracted Concept Representations

Roel Visser, Isaac Roberts, Barbara Hammer

The paper proposes Contrastive Concept Importance (CCI), a method that attributes the logit margin between a target and a foil class to automatically extracted visual concepts, pro…

#explainable ai#concept-based explanations#contrastive attribution#visual concepts
cs.CR2026

Benign on Label, Malicious by Design: Clean-Label Dormant-to-Activated Backdoor via Machine Unlearning with Removable Camouflage

Dongdong Zhao, Can Li, Xiang Yao +3

The paper proposes a clean‑label backdoor attack that stays dormant during training and becomes active only after specific camouflage samples are removed via machine unlearning, us…

#backdoor attacks#machine unlearning#clean-label#adversarial machine learning
cs.LG2026

Improving the Robustness/Accuracy Tradeoff Against Adversarial Attacks Using Information Bottleneck Distillation Through Dual Teachers

Vincent Ryusuke Takahashi, Yoshinari Takeishi, Jun'ichi Takeuchi +1

The paper extends information bottleneck distillation by adding a clean‑trained teacher alongside a robust teacher, using cross‑layer attention to improve both clean accuracy and a…

#adversarial robustness#knowledge distillation#information bottleneck#dual teacher
cs.AI2026

Simplifying Neural Networks During Training

Lorenzo Sciandra, Samuele Fonio, Roberto Esposito

The paper proposes a training framework that monitors representation dynamics using the Inverse Fisher Criterion to identify when and where to replace later layers of a deep networ…

#neural network pruning#training dynamics#neural collapse#model simplification
cs.CV2026

Representation Trajectories Matters: Complementary Evidence for OOD Detection and Image Classification

Ignacio M. De la Jara, Cristian Rodriguez-Opazo, Hamed Damirchi +2

The paper investigates how the step‑by‑step changes in a vision model’s internal representations (representation trajectories) can be used to improve out‑of‑distribution detection…

#out-of-distribution detection#representation trajectories#image classification#intermediate layer analysis
cs.CV2026

FunnelAL: Retrieve-then-Rank Active Learning for Single-Class Discovery

Reihaneh Rostami, Brian Goodwin

FunnelAL is an active learning system that first retrieves candidate images using embeddings and then ranks them to efficiently discover a single target class while minimizing anno…

#active learning#single-class discovery#image classification#retrieval
cs.CV2026

Lightweight Image Classification of Raptor Species for Edge Devices: Rare-Species Dataset Expansion via Video Frame Extraction, Knowledge Distillation, and TensorRT Deployment

Takeshi Nishikawa

The paper presents a lightweight model ensemble for classifying raptor species on edge devices, using knowledge distillation from a large teacher model and expanding the dataset vi…

#image classification#edge computing#knowledge distillation#dataset expansion
cs.CV2026

When Pretty Isn't Useful: Investigating Why Modern Text-to-Image Models Fail as Reliable Training Data Generators

Krzysztof Adamkiewicz, Brian Bernhard Moser, Stanislav Frolov +3

The paper evaluates modern text-to-image diffusion models as sources of synthetic training data and finds that, despite higher visual quality, newer models produce less diverse ima…

#text-to-image generation#synthetic data#image classification#data diversity
cs.CV2026

Screening Is Effective for Visual Recognition

Shunya Shimomura, Kazuhiro Hotta

The paper proposes VisionScreen, a model that applies a screening mechanism to evaluate and select relevant image patches independently, improving visual recognition performance co…

#vision transformers#screening mechanism#image classification#patch selection
gr-qc2026

Gravitational lensing of gravitational waves: universal characteristics of strongly lensed memory waveforms

Ruanjing Zhang, Zhi-Chao Zhao, Shaoqi Hou +3

The paper analyzes how strong gravitational lensing alters the gravitational‑wave memory signal, revealing universal, image‑type‑dependent waveform features that are independent of…

#gravitational lensing#gravitational wave memory#strong lensing#waveform morphology
cs.CV2026

Data Safety: Synthetic Data Quality Analysis Using CIFAKE Dataset

Kuniko Paxton, Amila Akagić, Koorosh Aslansefat +2

The paper examines how synthetic images generated by different methods differ from real images in feature space, color statistics, and model training, and proposes strategies for e…

#synthetic data#image classification#data quality assessment#feature space analysis

One search, two signals: results blend meaning (embedding similarity, so papers that never use your words still surface) with keyword matches on titles, abstracts and summaries. Free, no sign-in needed.