2021 IEEE International Conference on Image Processing
19-22 September 2021 • Anchorage, Alaska, USA
Imaging Without Borders
All times are in Alaska local time (AKDT/UTC−08:00)
MLR-APPL-IP-5: Machine learning for image processing 5 |
| Interactive Q&A Time: Tuesday, September 21, 13:30 - 15:00 |
| Session Chair: Chee Seng Chan, University of Malaya |
| MLR-APPL-IP-5.1: UNIVERSAL ADVERSARIAL ROBUSTNESS OF TEXTURE AND SHAPE-BIASED MODELS |
| Kenneth Co; Imperial College London |
| Luis Muñoz-González; Imperial College London |
| Leslie Kanthan; DataSpartan |
| Ben Glocker; Imperial College London |
| Emil Lupu; Imperial College London |
| MLR-APPL-IP-5.2: WEIGHTED AVERAGE PRECISION: ADVERSARIAL EXAMPLE DETECTION FOR VISUAL PERCEPTION OF AUTONOMOUS VEHICLES |
| Weiheng Chai; Syracuse University |
| Yantao Lu; Syracuse University |
| Senem Velipasalar; Syracuse University |
| MLR-APPL-IP-5.3: FABRICATE-VANISH: AN EFFECTIVE AND TRANSFERABLE BLACK-BOX ADVERSARIAL ATTACK INCORPORATING FEATURE DISTORTION |
| Yantao Lu; Syracuse University |
| Xueying Du; Northwestern Polytechnical University |
| Bingkun Sun; Northwestern Polytechnical University |
| Haining Ren; Purdue University |
| Senem Velipasalar; Syracuse University |
| MLR-APPL-IP-5.4: ADVERSARIAL TRAINING WITH STOCHASTIC WEIGHT AVERAGE |
| Joong-Won Hwang; Electronics and Telecommunications Research Institute |
| Youngwan Lee; Electronics and Telecommunications Research Institute |
| Sungchan Oh; Electronics and Telecommunications Research Institute |
| Yuseok Bae; Electronics and Telecommunications Research Institute |
| MLR-APPL-IP-5.5: SIMTROJAN: STEALTHY BACKDOOR ATTACK |
| Yankun Ren; Ant Group |
| Longfei Li; Ant Group |
| Jun Zhou; Ant Group |
| MLR-APPL-IP-5.6: INTELLIGENT AND ADAPTIVE MIXUP TECHNIQUE FOR ADVERSARIAL ROBUSTNESS |
| Akshay Agarwal; SUNY Buffalo |
| Mayank Vatsa; Indian Institute of Technology Jodhpur |
| Richa Singh; Indian Institute of Technology Jodhpur |
| Nalini Ratha; SUNY Buffalo |
| MLR-APPL-IP-5.7: IMPROVING FILLING LEVEL CLASSIFICATION WITH ADVERSARIAL TRAINING |
| Apostolos Modas; École Polytechnique Fédérale de Lausanne (EPFL) |
| Alessio Xompero; Queen Mary University of London |
| Ricardo Sánchez-Matilla; Queen Mary University of London |
| Pascal Frossard; École Polytechnique Fédérale de Lausanne (EPFL) |
| Andrea Cavallaro; Queen Mary University of London |
| MLR-APPL-IP-5.8: GENERATING ANNOTATED HIGH-FIDELITY IMAGES CONTAINING MULTIPLE COHERENT OBJECTS |
| Bryan Cardenas Guevara; University of Amsterdam |
| Devanshu Arya; University of Amsterdam |
| Deepak K. Gupta; University of Amsterdam |
| MLR-APPL-IP-5.9: A HYPERSPECTRAL APPROACH FOR UNSUPERVISED SPOOF DETECTION WITH INTRA-SAMPLE DISTRIBUTION |
| Tomoya Kaichi; Keio University |
| Yuko Ozasa; Tokyo Denki University |
| MLR-APPL-IP-5.10: PART-BASED FEATURE SQUEEZING TO DETECT ADVERSARIAL EXAMPLES IN PERSON RE-IDENTIFICATION NETWORKS |
| Yu Zheng; Syracuse University |
| Senem Velipasalar; Syracuse University |
| MLR-APPL-IP-5.11: SQUEEZE AND RECONSTRUCT: IMPROVED PRACTICAL ADVERSARIAL DEFENSE USING PAIRED IMAGE COMPRESSION AND RECONSTRUCTION |
| Bo-Han Kung; Research Center for Information Technology Innovation, Academia Sinica |
| Pin-Chun Chen; Research Center for Information Technology Innovation, Academia Sinica |
| Yu-Cheng Liu; Research Center for Information Technology Innovation, Academia Sinica |
| Jun-Cheng Chen; Research Center for Information Technology Innovation, Academia Sinica |