Notice: Function _load_textdomain_just_in_time was called incorrectly. Translation loading for the jwt-auth domain was triggered too early. This is usually an indicator for some code in the plugin or theme running too early. Translations should be loaded at the init action or later. Please see Debugging in WordPress for more information. (This message was added in version 6.7.0.) in /home/forge/wikicram.com/wp-includes/functions.php on line 6121
Notice: Function _load_textdomain_just_in_time was called incorrectly. Translation loading for the wck domain was triggered too early. This is usually an indicator for some code in the plugin or theme running too early. Translations should be loaded at the init action or later. Please see Debugging in WordPress for more information. (This message was added in version 6.7.0.) in /home/forge/wikicram.com/wp-includes/functions.php on line 6121 You have a dataset of face images at 128×128 resolution, som… | Wiki CramSkip to main navigationSkip to main contentSkip to footer
You have a dataset of face images at 128×128 resolution, som…
You have a dataset of face images at 128×128 resolution, some are severely noisy (grainy camera shots). You want to classify each image into one of five expressions: happy, sad, angry, surprised, neutral. You decide to build: Autoencoder (AE) for denoising. CNN that classifies the AE’s output. GAN for data augmentation—generating extra images in each expression category. After some early success, you suspect domain mismatch and overfitting. Let’s see what goes wrong. — You see that many final images lose fine expression cues—like subtle eyebrow changes—once the AE cleans them. The CNN’s accuracy on “angry” and “sad” is low. What’s the most likely conceptual reason? (Select one correct answer)
You have a dataset of face images at 128×128 resolution, som…
Questions
Yоu hаve а dаtaset оf face images at 128×128 resоlution, some are severely noisy (grainy camera shots). You want to classify each image into one of five expressions: happy, sad, angry, surprised, neutral. You decide to build: Autoencoder (AE) for denoising. CNN that classifies the AE’s output. GAN for data augmentation—generating extra images in each expression category. After some early success, you suspect domain mismatch and overfitting. Let’s see what goes wrong. --- You see that many final images lose fine expression cues—like subtle eyebrow changes—once the AE cleans them. The CNN’s accuracy on “angry” and “sad” is low. What’s the most likely conceptual reason? (Select one correct answer)